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

Dataset: Open Web Text

Neuron 474 in Layer 1

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: 3.7076. Min Range: -3.7076

Max Act: 3.7076. Min Act: -0.1700

Data Index: 563330 (Open Web Text)

Max Activating Token Index: 409

Text #1

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.7009. Min Act: -0.1700

Data Index: 6207211 (Open Web Text)

Max Activating Token Index: 735

Text #2

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6977. Min Act: -0.1700

Data Index: 829327 (Open Web Text)

Max Activating Token Index: 376

Text #3

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6855. Min Act: -0.1700

Data Index: 8571525 (Open Web Text)

Max Activating Token Index: 1017

Text #4

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6650. Min Act: -0.1700

Data Index: 4530205 (Open Web Text)

Max Activating Token Index: 944

Text #5

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6883. Min Act: -0.1700

Data Index: 387028 (Open Web Text)

Max Activating Token Index: 231

Text #6

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6845. Min Act: -0.1700

Data Index: 5998900 (Open Web Text)

Max Activating Token Index: 681

Text #7

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6644. Min Act: -0.1700

Data Index: 6486024 (Open Web Text)

Max Activating Token Index: 203

Text #8

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6800. Min Act: -0.1700

Data Index: 7923925 (Open Web Text)

Max Activating Token Index: 631

Text #9

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6438. Min Act: -0.1700

Data Index: 1378157 (Open Web Text)

Max Activating Token Index: 480

Text #10

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6356. Min Act: -0.1700

Data Index: 1115061 (Open Web Text)

Max Activating Token Index: 346

Text #11

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6668. Min Act: -0.1700

Data Index: 3304931 (Open Web Text)

Max Activating Token Index: 237

Text #12

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6410. Min Act: -0.1700

Data Index: 8452063 (Open Web Text)

Max Activating Token Index: 582

Text #13

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6373. Min Act: -0.1700

Data Index: 3163119 (Open Web Text)

Max Activating Token Index: 498

Text #14

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6414. Min Act: -0.1700

Data Index: 8299349 (Open Web Text)

Max Activating Token Index: 59

Text #15

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6446. Min Act: -0.1700

Data Index: 8014295 (Open Web Text)

Max Activating Token Index: 189

Text #16

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6337. Min Act: -0.1700

Data Index: 4955078 (Open Web Text)

Max Activating Token Index: 590

Text #17

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6502. Min Act: -0.1700

Data Index: 4161962 (Open Web Text)

Max Activating Token Index: 133

Text #18

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6467. Min Act: -0.1700

Data Index: 3618756 (Open Web Text)

Max Activating Token Index: 955

Text #19

Max Range: 3.7076. Min Range: -3.7076

Max Act: 3.6082. Min Act: -0.1700

Data Index: 1146106 (Open Web Text)

Max Activating Token Index: 157