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

Dataset: Open Web Text

Neuron 2682 in Layer 5

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: 5.2323. Min Range: -5.2323

Max Act: 5.2323. Min Act: -0.1700

Data Index: 4098856 (Open Web Text)

Max Activating Token Index: 993

Text #1

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.1072. Min Act: -0.1700

Data Index: 8299978 (Open Web Text)

Max Activating Token Index: 62

Text #2

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.0640. Min Act: -0.1700

Data Index: 2602888 (Open Web Text)

Max Activating Token Index: 83

Text #3

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.0376. Min Act: -0.1700

Data Index: 8432440 (Open Web Text)

Max Activating Token Index: 720

Text #4

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.9274. Min Act: -0.1700

Data Index: 1208886 (Open Web Text)

Max Activating Token Index: 630

Text #5

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.8793. Min Act: -0.1700

Data Index: 7790947 (Open Web Text)

Max Activating Token Index: 580

Text #6

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.9041. Min Act: -0.1700

Data Index: 3393149 (Open Web Text)

Max Activating Token Index: 1019

Text #7

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.8022. Min Act: -0.1700

Data Index: 6895186 (Open Web Text)

Max Activating Token Index: 107

Text #8

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.8030. Min Act: -0.1700

Data Index: 8483443 (Open Web Text)

Max Activating Token Index: 976

Text #9

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.7365. Min Act: -0.1700

Data Index: 8707240 (Open Web Text)

Max Activating Token Index: 241

Text #10

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.7077. Min Act: -0.1700

Data Index: 3124628 (Open Web Text)

Max Activating Token Index: 857

Text #11

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.7467. Min Act: -0.1700

Data Index: 33205 (Open Web Text)

Max Activating Token Index: 165

Text #12

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.7213. Min Act: -0.1700

Data Index: 2189614 (Open Web Text)

Max Activating Token Index: 63

Text #13

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.6954. Min Act: -0.1700

Data Index: 4356660 (Open Web Text)

Max Activating Token Index: 55

Text #14

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.7170. Min Act: -0.1700

Data Index: 3634606 (Open Web Text)

Max Activating Token Index: 131

Text #15

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.7310. Min Act: -0.1700

Data Index: 2983121 (Open Web Text)

Max Activating Token Index: 231

Text #16

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.6928. Min Act: -0.1700

Data Index: 6589408 (Open Web Text)

Max Activating Token Index: 419

Text #17

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.6768. Min Act: -0.1700

Data Index: 3672211 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.7211. Min Act: -0.1700

Data Index: 327732 (Open Web Text)

Max Activating Token Index: 958

Text #19

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.6733. Min Act: -0.1700

Data Index: 2924024 (Open Web Text)

Max Activating Token Index: 90