< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 3064 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.2157. Min Act: -0.1700

Data Index: 1470746 (Open Web Text)

Max Activating Token Index: 938

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.2089. Min Act: -0.1700

Data Index: 3978953 (Open Web Text)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.1633. Min Act: -0.1700

Data Index: 3138704 (Open Web Text)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.1732. Min Act: -0.1700

Data Index: 8649704 (Open Web Text)

Max Activating Token Index: 881

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.1532. Min Act: -0.1700

Data Index: 8455566 (Open Web Text)

Max Activating Token Index: 965

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.1391. Min Act: -0.1700

Data Index: 1740702 (Open Web Text)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.0881. Min Act: -0.1700

Data Index: 4353743 (Open Web Text)

Max Activating Token Index: 899

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.1257. Min Act: -0.1700

Data Index: 3123131 (Open Web Text)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.1404. Min Act: -0.1700

Data Index: 4292139 (Open Web Text)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.0882. Min Act: -0.1700

Data Index: 2787275 (Open Web Text)

Max Activating Token Index: 243

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.0766. Min Act: -0.1700

Data Index: 5923780 (Open Web Text)

Max Activating Token Index: 646

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.0712. Min Act: -0.1700

Data Index: 8452269 (Open Web Text)

Max Activating Token Index: 90

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.1126. Min Act: -0.1700

Data Index: 1651164 (Open Web Text)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.0666. Min Act: -0.1700

Data Index: 1969200 (Open Web Text)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.0605. Min Act: -0.1700

Data Index: 5445046 (Open Web Text)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.0743. Min Act: -0.1700

Data Index: 1651166 (Open Web Text)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.0753. Min Act: -0.1700

Data Index: 8358901 (Open Web Text)

Max Activating Token Index: 634

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.0551. Min Act: -0.1700

Data Index: 4093127 (Open Web Text)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.0707. Min Act: -0.1700

Data Index: 8254077 (Open Web Text)

Max Activating Token Index: 549

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.2157. Min Range: -2.2157

Max Act: 2.0746. Min Act: -0.1700

Data Index: 6537976 (Open Web Text)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #19