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

Dataset: Open Web Text

Neuron 1793 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: 3.9103. Min Range: -3.9103

Max Act: 3.9103. Min Act: -0.1700

Data Index: 7940480 (Open Web Text)

Max Activating Token Index: 620

Text #1

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.8528. Min Act: -0.1700

Data Index: 1051666 (Open Web Text)

Max Activating Token Index: 581

Text #2

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.8291. Min Act: -0.1700

Data Index: 1289318 (Open Web Text)

Max Activating Token Index: 38

Text #3

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.7868. Min Act: -0.1700

Data Index: 1579514 (Open Web Text)

Max Activating Token Index: 344

Text #4

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.8031. Min Act: -0.1700

Data Index: 814920 (Open Web Text)

Max Activating Token Index: 39

Text #5

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.7857. Min Act: -0.1700

Data Index: 2786715 (Open Web Text)

Max Activating Token Index: 281

Text #6

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.7849. Min Act: -0.1700

Data Index: 6880623 (Open Web Text)

Max Activating Token Index: 623

Text #7

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.7494. Min Act: -0.1700

Data Index: 4336355 (Open Web Text)

Max Activating Token Index: 493

Text #8

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.7630. Min Act: -0.1700

Data Index: 1869210 (Open Web Text)

Max Activating Token Index: 229

Text #9

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.7427. Min Act: -0.1700

Data Index: 4174356 (Open Web Text)

Max Activating Token Index: 489

Text #10

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.8072. Min Act: -0.1700

Data Index: 5620934 (Open Web Text)

Max Activating Token Index: 498

Text #11

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.7840. Min Act: -0.1700

Data Index: 6565637 (Open Web Text)

Max Activating Token Index: 848

Text #12

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.7319. Min Act: -0.1700

Data Index: 3562077 (Open Web Text)

Max Activating Token Index: 204

Text #13

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.7587. Min Act: -0.1700

Data Index: 980630 (Open Web Text)

Max Activating Token Index: 916

Text #14

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.7449. Min Act: -0.1700

Data Index: 1115058 (Open Web Text)

Max Activating Token Index: 622

Text #15

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.7480. Min Act: -0.1700

Data Index: 2500164 (Open Web Text)

Max Activating Token Index: 72

Text #16

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.7362. Min Act: -0.1700

Data Index: 26920 (Open Web Text)

Max Activating Token Index: 904

Text #17

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.7397. Min Act: -0.1700

Data Index: 4512643 (Open Web Text)

Max Activating Token Index: 391

Text #18

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.6848. Min Act: -0.1700

Data Index: 805094 (Open Web Text)

Max Activating Token Index: 297

Text #19

Max Range: 3.9103. Min Range: -3.9103

Max Act: 3.6894. Min Act: -0.1700

Data Index: 4285609 (Open Web Text)

Max Activating Token Index: 308