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

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

Neuron 762 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: 0.0323. Min Range: -0.0323

Max Act: 0.0323. Min Act: -0.0006

Data Index: 319860 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0300. Min Act: -0.0006

Data Index: 907427 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0296. Min Act: -0.0006

Data Index: 687337 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0285. Min Act: -0.0006

Data Index: 1244353 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0261. Min Act: -0.0006

Data Index: 180240 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1263196 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1152275 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0260. Min Act: -0.0006

Data Index: 1281254 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0255. Min Act: -0.0006

Data Index: 38989 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0259. Min Act: -0.0006

Data Index: 738950 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0252. Min Act: -0.0006

Data Index: 695389 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0250. Min Act: -0.0006

Data Index: 236412 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0246. Min Act: -0.0006

Data Index: 902854 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0251. Min Act: -0.0006

Data Index: 853472 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0255. Min Act: -0.0006

Data Index: 314044 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0243. Min Act: -0.0006

Data Index: 579175 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0253. Min Act: -0.0006

Data Index: 34494 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0247. Min Act: -0.0006

Data Index: 415813 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0246. Min Act: -0.0006

Data Index: 75508 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0233. Min Act: -0.0006

Data Index: 140036 (C4 (Web Text))

Max Activating Token Index: 419