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

Dataset: Open Web Text

Neuron 600 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: 4.6885. Min Range: -4.6885

Max Act: 4.6885. Min Act: -0.1700

Data Index: 2843835 (Open Web Text)

Max Activating Token Index: 248

Text #1

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.6197. Min Act: -0.1700

Data Index: 4120183 (Open Web Text)

Max Activating Token Index: 983

Text #2

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.5389. Min Act: -0.1700

Data Index: 3847442 (Open Web Text)

Max Activating Token Index: 569

Text #3

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.5166. Min Act: -0.1700

Data Index: 5698777 (Open Web Text)

Max Activating Token Index: 179

Text #4

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.5328. Min Act: -0.1700

Data Index: 1502752 (Open Web Text)

Max Activating Token Index: 209

Text #5

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.5326. Min Act: -0.1700

Data Index: 5232339 (Open Web Text)

Max Activating Token Index: 621

Text #6

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.5283. Min Act: -0.1700

Data Index: 6368625 (Open Web Text)

Max Activating Token Index: 679

Text #7

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.5210. Min Act: -0.1700

Data Index: 8304548 (Open Web Text)

Max Activating Token Index: 526

Text #8

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.4934. Min Act: -0.1700

Data Index: 5933208 (Open Web Text)

Max Activating Token Index: 718

Text #9

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.4797. Min Act: -0.1700

Data Index: 2245980 (Open Web Text)

Max Activating Token Index: 113

Text #10

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.4714. Min Act: -0.1700

Data Index: 2426389 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.4193. Min Act: -0.1700

Data Index: 5645499 (Open Web Text)

Max Activating Token Index: 305

Text #12

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.4253. Min Act: -0.1700

Data Index: 7970019 (Open Web Text)

Max Activating Token Index: 870

Text #13

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.4361. Min Act: -0.1700

Data Index: 7587720 (Open Web Text)

Max Activating Token Index: 34

Text #14

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.4091. Min Act: -0.1700

Data Index: 501612 (Open Web Text)

Max Activating Token Index: 937

Text #15

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.4278. Min Act: -0.1700

Data Index: 1238179 (Open Web Text)

Max Activating Token Index: 912

Text #16

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.4229. Min Act: -0.1700

Data Index: 2927345 (Open Web Text)

Max Activating Token Index: 55

Text #17

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.4120. Min Act: -0.1700

Data Index: 455532 (Open Web Text)

Max Activating Token Index: 211

Text #18

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.4330. Min Act: -0.1700

Data Index: 943865 (Open Web Text)

Max Activating Token Index: 733

Text #19

Max Range: 4.6885. Min Range: -4.6885

Max Act: 4.3697. Min Act: -0.1700

Data Index: 6297514 (Open Web Text)

Max Activating Token Index: 24