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

Dataset: Open Web Text

Neuron 396 in Layer 6

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: 7.1867. Min Range: -7.1867

Max Act: 7.1867. Min Act: -0.1700

Data Index: 3934415 (Open Web Text)

Max Activating Token Index: 872

Text #1

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.9162. Min Act: -0.1700

Data Index: 1252115 (Open Web Text)

Max Activating Token Index: 582

Text #2

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.5250. Min Act: -0.1700

Data Index: 6703876 (Open Web Text)

Max Activating Token Index: 251

Text #3

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.5026. Min Act: -0.1700

Data Index: 8110457 (Open Web Text)

Max Activating Token Index: 537

Text #4

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.4414. Min Act: -0.1700

Data Index: 6606375 (Open Web Text)

Max Activating Token Index: 366

Text #5

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.3973. Min Act: -0.1700

Data Index: 6936951 (Open Web Text)

Max Activating Token Index: 459

Text #6

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.4413. Min Act: -0.1700

Data Index: 1847162 (Open Web Text)

Max Activating Token Index: 880

Text #7

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.3981. Min Act: -0.1700

Data Index: 7400134 (Open Web Text)

Max Activating Token Index: 981

Text #8

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.3714. Min Act: -0.1700

Data Index: 4116595 (Open Web Text)

Max Activating Token Index: 264

Text #9

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.3336. Min Act: -0.1700

Data Index: 4038169 (Open Web Text)

Max Activating Token Index: 632

Text #10

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.3531. Min Act: -0.1700

Data Index: 6254115 (Open Web Text)

Max Activating Token Index: 641

Text #11

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.3233. Min Act: -0.1700

Data Index: 103536 (Open Web Text)

Max Activating Token Index: 344

Text #12

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.3059. Min Act: -0.1700

Data Index: 6110474 (Open Web Text)

Max Activating Token Index: 50

Text #13

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.2669. Min Act: -0.1700

Data Index: 3280943 (Open Web Text)

Max Activating Token Index: 515

Text #14

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.3282. Min Act: -0.1700

Data Index: 4940721 (Open Web Text)

Max Activating Token Index: 956

Text #15

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.2878. Min Act: -0.1700

Data Index: 4492921 (Open Web Text)

Max Activating Token Index: 827

Text #16

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.2629. Min Act: -0.1700

Data Index: 4987347 (Open Web Text)

Max Activating Token Index: 717

Text #17

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.2867. Min Act: -0.1700

Data Index: 7382006 (Open Web Text)

Max Activating Token Index: 683

Text #18

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.2652. Min Act: -0.1700

Data Index: 4233424 (Open Web Text)

Max Activating Token Index: 399

Text #19

Max Range: 7.1867. Min Range: -7.1867

Max Act: 6.1995. Min Act: -0.1700

Data Index: 8010565 (Open Web Text)

Max Activating Token Index: 589