< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 87 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.8227. Min Act: -0.1700

Data Index: 7337240 (Open Web Text)

Max Activating Token Index: 839

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.7475. Min Act: -0.1700

Data Index: 3414930 (Open Web Text)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.7338. Min Act: -0.1700

Data Index: 8541746 (Open Web Text)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.7180. Min Act: -0.1700

Data Index: 1679005 (Open Web Text)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.7176. Min Act: -0.1700

Data Index: 4968864 (Open Web Text)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.7069. Min Act: -0.1700

Data Index: 1149480 (Open Web Text)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.6749. Min Act: -0.1700

Data Index: 339371 (Open Web Text)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.6636. Min Act: -0.1700

Data Index: 4743135 (Open Web Text)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.6672. Min Act: -0.1700

Data Index: 3018694 (Open Web Text)

Max Activating Token Index: 623

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.6642. Min Act: -0.1700

Data Index: 775247 (Open Web Text)

Max Activating Token Index: 253

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.6332. Min Act: -0.1700

Data Index: 6419793 (Open Web Text)

Max Activating Token Index: 435

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.6241. Min Act: -0.1700

Data Index: 7014401 (Open Web Text)

Max Activating Token Index: 331

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.6310. Min Act: -0.1700

Data Index: 5368089 (Open Web Text)

Max Activating Token Index: 88

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.6276. Min Act: -0.1700

Data Index: 978965 (Open Web Text)

Max Activating Token Index: 272

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.6305. Min Act: -0.1700

Data Index: 8469328 (Open Web Text)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.6196. Min Act: -0.1700

Data Index: 356206 (Open Web Text)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.6099. Min Act: -0.1700

Data Index: 6784027 (Open Web Text)

Max Activating Token Index: 883

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.6289. Min Act: -0.1700

Data Index: 2642930 (Open Web Text)

Max Activating Token Index: 249

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.6326. Min Act: -0.1700

Data Index: 8125312 (Open Web Text)

Max Activating Token Index: 207

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8227. Min Range: -2.8227

Max Act: 2.6325. Min Act: -0.1700

Data Index: 460133 (Open Web Text)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #19