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

Dataset: Open Web Text

Neuron 906 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: 4.6162. Min Range: -4.6162

Max Act: 4.6162. Min Act: -0.1700

Data Index: 7015453 (Open Web Text)

Max Activating Token Index: 148

Text #1

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.5208. Min Act: -0.1700

Data Index: 7576719 (Open Web Text)

Max Activating Token Index: 258

Text #2

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.4881. Min Act: -0.1700

Data Index: 7975996 (Open Web Text)

Max Activating Token Index: 689

Text #3

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.4552. Min Act: -0.1700

Data Index: 1872360 (Open Web Text)

Max Activating Token Index: 844

Text #4

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.4753. Min Act: -0.1700

Data Index: 3230701 (Open Web Text)

Max Activating Token Index: 298

Text #5

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.4112. Min Act: -0.1700

Data Index: 2497962 (Open Web Text)

Max Activating Token Index: 294

Text #6

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.4169. Min Act: -0.1700

Data Index: 3401350 (Open Web Text)

Max Activating Token Index: 325

Text #7

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.4319. Min Act: -0.1700

Data Index: 7163458 (Open Web Text)

Max Activating Token Index: 627

Text #8

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.4302. Min Act: -0.1700

Data Index: 2225184 (Open Web Text)

Max Activating Token Index: 120

Text #9

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.4485. Min Act: -0.1700

Data Index: 3390518 (Open Web Text)

Max Activating Token Index: 911

Text #10

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.4228. Min Act: -0.1700

Data Index: 8113146 (Open Web Text)

Max Activating Token Index: 331

Text #11

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.4121. Min Act: -0.1700

Data Index: 1828181 (Open Web Text)

Max Activating Token Index: 341

Text #12

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.3930. Min Act: -0.1700

Data Index: 7312984 (Open Web Text)

Max Activating Token Index: 465

Text #13

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.3741. Min Act: -0.1700

Data Index: 5706313 (Open Web Text)

Max Activating Token Index: 536

Text #14

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.3817. Min Act: -0.1700

Data Index: 4429902 (Open Web Text)

Max Activating Token Index: 83

Text #15

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.3340. Min Act: -0.1700

Data Index: 4173823 (Open Web Text)

Max Activating Token Index: 214

Text #16

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.3293. Min Act: -0.1700

Data Index: 4696356 (Open Web Text)

Max Activating Token Index: 168

Text #17

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.3195. Min Act: -0.1700

Data Index: 526876 (Open Web Text)

Max Activating Token Index: 690

Text #18

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.3355. Min Act: -0.1700

Data Index: 4046738 (Open Web Text)

Max Activating Token Index: 919

Text #19

Max Range: 4.6162. Min Range: -4.6162

Max Act: 4.3408. Min Act: -0.1700

Data Index: 1607436 (Open Web Text)

Max Activating Token Index: 806