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

Dataset: Open Web Text

Neuron 1694 in Layer 3

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: 4.7165. Min Range: -4.7165

Max Act: 4.7165. Min Act: -0.1700

Data Index: 3107237 (Open Web Text)

Max Activating Token Index: 1017

Text #1

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.6551. Min Act: -0.1700

Data Index: 4815437 (Open Web Text)

Max Activating Token Index: 571

Text #2

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.6198. Min Act: -0.1700

Data Index: 3121277 (Open Web Text)

Max Activating Token Index: 56

Text #3

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.5999. Min Act: -0.1700

Data Index: 1140084 (Open Web Text)

Max Activating Token Index: 474

Text #4

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.5567. Min Act: -0.1700

Data Index: 5194924 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.5478. Min Act: -0.1700

Data Index: 4038896 (Open Web Text)

Max Activating Token Index: 43

Text #6

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.5425. Min Act: -0.1700

Data Index: 5027913 (Open Web Text)

Max Activating Token Index: 235

Text #7

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.5277. Min Act: -0.1700

Data Index: 5848010 (Open Web Text)

Max Activating Token Index: 965

Text #8

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.5264. Min Act: -0.1700

Data Index: 2600971 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.5212. Min Act: -0.1700

Data Index: 8656735 (Open Web Text)

Max Activating Token Index: 43

Text #10

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.5176. Min Act: -0.1700

Data Index: 2034695 (Open Web Text)

Max Activating Token Index: 376

Text #11

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.5235. Min Act: -0.1700

Data Index: 6933940 (Open Web Text)

Max Activating Token Index: 846

Text #12

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.5504. Min Act: -0.1700

Data Index: 3034067 (Open Web Text)

Max Activating Token Index: 906

Text #13

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.5170. Min Act: -0.1700

Data Index: 6348459 (Open Web Text)

Max Activating Token Index: 41

Text #14

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.5434. Min Act: -0.1700

Data Index: 4759779 (Open Web Text)

Max Activating Token Index: 69

Text #15

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.5151. Min Act: -0.1700

Data Index: 3635512 (Open Web Text)

Max Activating Token Index: 293

Text #16

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.4959. Min Act: -0.1700

Data Index: 2559769 (Open Web Text)

Max Activating Token Index: 879

Text #17

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.4858. Min Act: -0.1700

Data Index: 5045914 (Open Web Text)

Max Activating Token Index: 831

Text #18

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.4654. Min Act: -0.1700

Data Index: 2916387 (Open Web Text)

Max Activating Token Index: 1010

Text #19

Max Range: 4.7165. Min Range: -4.7165

Max Act: 4.5052. Min Act: -0.1700

Data Index: 2969088 (Open Web Text)

Max Activating Token Index: 798