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

Dataset: Open Web Text

Neuron 173 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: 3.1942. Min Range: -3.1942

Max Act: 3.1942. Min Act: -0.1700

Data Index: 1848914 (Open Web Text)

Max Activating Token Index: 339

Text #1

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0488. Min Act: -0.1700

Data Index: 8453565 (Open Web Text)

Max Activating Token Index: 668

Text #2

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0214. Min Act: -0.1700

Data Index: 4381439 (Open Web Text)

Max Activating Token Index: 63

Text #3

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0355. Min Act: -0.1700

Data Index: 3902665 (Open Web Text)

Max Activating Token Index: 947

Text #4

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0137. Min Act: -0.1700

Data Index: 3230020 (Open Web Text)

Max Activating Token Index: 99

Text #5

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0263. Min Act: -0.1700

Data Index: 8786198 (Open Web Text)

Max Activating Token Index: 799

Text #6

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0054. Min Act: -0.1700

Data Index: 2105187 (Open Web Text)

Max Activating Token Index: 447

Text #7

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0032. Min Act: -0.1700

Data Index: 197956 (Open Web Text)

Max Activating Token Index: 887

Text #8

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0215. Min Act: -0.1700

Data Index: 2470532 (Open Web Text)

Max Activating Token Index: 689

Text #9

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.9896. Min Act: -0.1700

Data Index: 8572418 (Open Web Text)

Max Activating Token Index: 356

Text #10

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.9823. Min Act: -0.1700

Data Index: 1053320 (Open Web Text)

Max Activating Token Index: 147

Text #11

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.9386. Min Act: -0.1700

Data Index: 3092773 (Open Web Text)

Max Activating Token Index: 900

Text #12

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.9439. Min Act: -0.1700

Data Index: 6794075 (Open Web Text)

Max Activating Token Index: 50

Text #13

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.9363. Min Act: -0.1700

Data Index: 3955257 (Open Web Text)

Max Activating Token Index: 204

Text #14

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.9461. Min Act: -0.1700

Data Index: 2668042 (Open Web Text)

Max Activating Token Index: 848

Text #15

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.9582. Min Act: -0.1700

Data Index: 1746489 (Open Web Text)

Max Activating Token Index: 790

Text #16

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.9335. Min Act: -0.1700

Data Index: 1890390 (Open Web Text)

Max Activating Token Index: 735

Text #17

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.9303. Min Act: -0.1700

Data Index: 4411280 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.9236. Min Act: -0.1700

Data Index: 218528 (Open Web Text)

Max Activating Token Index: 116

Text #19

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.8897. Min Act: -0.1700

Data Index: 802162 (Open Web Text)

Max Activating Token Index: 463