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

Dataset: Open Web Text

Neuron 1200 in Layer 2

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: 1.3870. Min Range: -1.3870

Max Act: 1.3870. Min Act: -0.1700

Data Index: 7492014 (Open Web Text)

Max Activating Token Index: 192

Text #1

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3823. Min Act: -0.1700

Data Index: 2153235 (Open Web Text)

Max Activating Token Index: 776

Text #2

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3796. Min Act: -0.1699

Data Index: 3646726 (Open Web Text)

Max Activating Token Index: 489

Text #3

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3548. Min Act: -0.1699

Data Index: 642998 (Open Web Text)

Max Activating Token Index: 216

Text #4

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3540. Min Act: -0.1700

Data Index: 6400093 (Open Web Text)

Max Activating Token Index: 163

Text #5

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3475. Min Act: -0.1699

Data Index: 6112087 (Open Web Text)

Max Activating Token Index: 305

Text #6

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3550. Min Act: -0.1699

Data Index: 4101452 (Open Web Text)

Max Activating Token Index: 750

Text #7

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3485. Min Act: -0.1700

Data Index: 335456 (Open Web Text)

Max Activating Token Index: 360

Text #8

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3393. Min Act: -0.1700

Data Index: 3483825 (Open Web Text)

Max Activating Token Index: 114

Text #9

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3286. Min Act: -0.1700

Data Index: 1154757 (Open Web Text)

Max Activating Token Index: 907

Text #10

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3276. Min Act: -0.1699

Data Index: 7175527 (Open Web Text)

Max Activating Token Index: 343

Text #11

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3263. Min Act: -0.1700

Data Index: 8743442 (Open Web Text)

Max Activating Token Index: 740

Text #12

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3367. Min Act: -0.1692

Data Index: 2338591 (Open Web Text)

Max Activating Token Index: 660

Text #13

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3244. Min Act: -0.1683

Data Index: 3646725 (Open Web Text)

Max Activating Token Index: 117

Text #14

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3185. Min Act: -0.1700

Data Index: 768068 (Open Web Text)

Max Activating Token Index: 330

Text #15

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3147. Min Act: -0.1700

Data Index: 4476078 (Open Web Text)

Max Activating Token Index: 699

Text #16

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3330. Min Act: -0.1674

Data Index: 6698708 (Open Web Text)

Max Activating Token Index: 637

Text #17

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3202. Min Act: -0.1700

Data Index: 1498327 (Open Web Text)

Max Activating Token Index: 928

Text #18

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3242. Min Act: -0.1687

Data Index: 2338594 (Open Web Text)

Max Activating Token Index: 660

Text #19

Max Range: 1.3870. Min Range: -1.3870

Max Act: 1.3117. Min Act: -0.1687

Data Index: 2158002 (Open Web Text)

Max Activating Token Index: 528