< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 535 in Layer 5

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: 2.5105. Min Range: -2.5105

Max Act: 2.4898. Min Act: -0.1700

Data Index: 5047244 (Open Web Text)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.5105. Min Act: -0.1700

Data Index: 1880467 (Open Web Text)

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.4949. Min Act: -0.1700

Data Index: 7394208 (Open Web Text)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.4621. Min Act: -0.1700

Data Index: 5239195 (Open Web Text)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.4698. Min Act: -0.1700

Data Index: 3513725 (Open Web Text)

Max Activating Token Index: 669

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.4816. Min Act: -0.1700

Data Index: 5093093 (Open Web Text)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.4502. Min Act: -0.1700

Data Index: 1931521 (Open Web Text)

Max Activating Token Index: 983

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.4398. Min Act: -0.1700

Data Index: 6872475 (Open Web Text)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.4408. Min Act: -0.1700

Data Index: 7367637 (Open Web Text)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.4559. Min Act: -0.1700

Data Index: 562063 (Open Web Text)

Max Activating Token Index: 292

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.4290. Min Act: -0.1700

Data Index: 1604229 (Open Web Text)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.4223. Min Act: -0.1700

Data Index: 6498103 (Open Web Text)

Max Activating Token Index: 79

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.3975. Min Act: -0.1700

Data Index: 6545807 (Open Web Text)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.4029. Min Act: -0.1700

Data Index: 5863511 (Open Web Text)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.4023. Min Act: -0.1700

Data Index: 8138142 (Open Web Text)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.4029. Min Act: -0.1700

Data Index: 118819 (Open Web Text)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.3901. Min Act: -0.1700

Data Index: 3015952 (Open Web Text)

Max Activating Token Index: 23

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.3758. Min Act: -0.1700

Data Index: 4144964 (Open Web Text)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.3975. Min Act: -0.1700

Data Index: 5186443 (Open Web Text)

Max Activating Token Index: 357

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.5105. Min Range: -2.5105

Max Act: 2.3720. Min Act: -0.1700

Data Index: 5956242 (Open Web Text)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #19