< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 87 in Layer 2

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: 2.2910. Min Range: -2.2910

Max Act: 2.2910. Min Act: -0.1700

Data Index: 183449 (Open Web Text)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.2230. Min Act: -0.1700

Data Index: 1154564 (Open Web Text)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.2061. Min Act: -0.1700

Data Index: 928460 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.2101. Min Act: -0.1700

Data Index: 6973804 (Open Web Text)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.1773. Min Act: -0.1700

Data Index: 3707806 (Open Web Text)

Max Activating Token Index: 266

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.1795. Min Act: -0.1700

Data Index: 1154565 (Open Web Text)

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.1654. Min Act: -0.1700

Data Index: 7297846 (Open Web Text)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.1490. Min Act: -0.1700

Data Index: 5298908 (Open Web Text)

Max Activating Token Index: 868

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.1152. Min Act: -0.1700

Data Index: 5840925 (Open Web Text)

Max Activating Token Index: 741

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.1154. Min Act: -0.1700

Data Index: 8319297 (Open Web Text)

Max Activating Token Index: 469

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.1016. Min Act: -0.1700

Data Index: 6722571 (Open Web Text)

Max Activating Token Index: 779

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.1201. Min Act: -0.1700

Data Index: 7179071 (Open Web Text)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.1183. Min Act: -0.1700

Data Index: 3575679 (Open Web Text)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.1183. Min Act: -0.1700

Data Index: 7846521 (Open Web Text)

Max Activating Token Index: 168

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.0906. Min Act: -0.1700

Data Index: 4503562 (Open Web Text)

Max Activating Token Index: 216

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.0781. Min Act: -0.1700

Data Index: 3692584 (Open Web Text)

Max Activating Token Index: 949

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.0909. Min Act: -0.1700

Data Index: 7966776 (Open Web Text)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.0739. Min Act: -0.1700

Data Index: 6140611 (Open Web Text)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.0838. Min Act: -0.1700

Data Index: 1176372 (Open Web Text)

Max Activating Token Index: 112

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.2910. Min Range: -2.2910

Max Act: 2.0884. Min Act: -0.1700

Data Index: 6375001 (Open Web Text)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #19