Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 465 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1408. Min Act: -0.0002

Data Index: 692329 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1357. Min Act: -0.0002

Data Index: 281824 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1219. Min Act: -0.0002

Data Index: 318982 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1323. Min Act: -0.0002

Data Index: 856938 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1256. Min Act: -0.0002

Data Index: 9180 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1273. Min Act: -0.0002

Data Index: 477697 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1282. Min Act: -0.0002

Data Index: 573315 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1358. Min Act: -0.0002

Data Index: 588123 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1366. Min Act: -0.0002

Data Index: 49760 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1217. Min Act: -0.0002

Data Index: 1194870 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1253. Min Act: -0.0002

Data Index: 1049212 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1235. Min Act: -0.0002

Data Index: 584447 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1270. Min Act: -0.0002

Data Index: 1105222 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1206. Min Act: -0.0002

Data Index: 564309 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1205. Min Act: -0.0002

Data Index: 454532 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1251. Min Act: -0.0002

Data Index: 109309 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1276. Min Act: -0.0002

Data Index: 1305454 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1255. Min Act: -0.0002

Data Index: 1082554 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1252. Min Act: -0.0002

Data Index: 227463 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1306. Min Act: -0.0002

Data Index: 271364 (C4 (Web Text))

Max Activating Token Index: 502