Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 487 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0288. Min Act: -0.0006

Data Index: 925359 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0264. Min Act: -0.0006

Data Index: 436115 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0282. Min Act: -0.0006

Data Index: 308127 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0267. Min Act: -0.0006

Data Index: 735380 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1262428 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0253. Min Act: -0.0006

Data Index: 479898 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0246. Min Act: -0.0006

Data Index: 617011 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1310810 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0236. Min Act: -0.0006

Data Index: 385548 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1067395 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0234. Min Act: -0.0006

Data Index: 705084 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0233. Min Act: -0.0006

Data Index: 56398 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0233. Min Act: -0.0006

Data Index: 686229 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0238. Min Act: -0.0006

Data Index: 109054 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1248553 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0222. Min Act: -0.0006

Data Index: 503104 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1177134 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0224. Min Act: -0.0006

Data Index: 203026 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0218. Min Act: -0.0006

Data Index: 707532 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1058074 (C4 (Web Text))

Max Activating Token Index: 551