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

Dataset: Open Web Text

Neuron 2712 in Layer 1

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: 3.8561. Min Range: -3.8561

Max Act: 3.8561. Min Act: -0.1700

Data Index: 4383944 (Open Web Text)

Max Activating Token Index: 571

Text #1

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.8089. Min Act: -0.1700

Data Index: 4392663 (Open Web Text)

Max Activating Token Index: 550

Text #2

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7358. Min Act: -0.1700

Data Index: 2612099 (Open Web Text)

Max Activating Token Index: 415

Text #3

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7264. Min Act: -0.1700

Data Index: 5985610 (Open Web Text)

Max Activating Token Index: 543

Text #4

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7417. Min Act: -0.1700

Data Index: 5693761 (Open Web Text)

Max Activating Token Index: 539

Text #5

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7406. Min Act: -0.1700

Data Index: 2839306 (Open Web Text)

Max Activating Token Index: 773

Text #6

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7268. Min Act: -0.1700

Data Index: 5621690 (Open Web Text)

Max Activating Token Index: 241

Text #7

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7632. Min Act: -0.1700

Data Index: 5187153 (Open Web Text)

Max Activating Token Index: 514

Text #8

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7281. Min Act: -0.1700

Data Index: 6333128 (Open Web Text)

Max Activating Token Index: 431

Text #9

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7271. Min Act: -0.1700

Data Index: 5139810 (Open Web Text)

Max Activating Token Index: 780

Text #10

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7565. Min Act: -0.1700

Data Index: 2209875 (Open Web Text)

Max Activating Token Index: 347

Text #11

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7344. Min Act: -0.1700

Data Index: 8695462 (Open Web Text)

Max Activating Token Index: 273

Text #12

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7357. Min Act: -0.1700

Data Index: 8654816 (Open Web Text)

Max Activating Token Index: 788

Text #13

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7526. Min Act: -0.1700

Data Index: 4226503 (Open Web Text)

Max Activating Token Index: 548

Text #14

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7532. Min Act: -0.1700

Data Index: 8462192 (Open Web Text)

Max Activating Token Index: 334

Text #15

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7097. Min Act: -0.1700

Data Index: 5181006 (Open Web Text)

Max Activating Token Index: 545

Text #16

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7250. Min Act: -0.1700

Data Index: 2760966 (Open Web Text)

Max Activating Token Index: 388

Text #17

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7020. Min Act: -0.1700

Data Index: 5566284 (Open Web Text)

Max Activating Token Index: 504

Text #18

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.6961. Min Act: -0.1700

Data Index: 56046 (Open Web Text)

Max Activating Token Index: 313

Text #19

Max Range: 3.8561. Min Range: -3.8561

Max Act: 3.7087. Min Act: -0.1700

Data Index: 3797819 (Open Web Text)

Max Activating Token Index: 293