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

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

Neuron 424 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0462. Min Act: -0.0005

Data Index: 290833 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0452. Min Act: -0.0005

Data Index: 320113 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0438. Min Act: -0.0005

Data Index: 801545 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0428. Min Act: -0.0005

Data Index: 812289 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0393. Min Act: -0.0005

Data Index: 192750 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0433. Min Act: -0.0005

Data Index: 626410 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0372. Min Act: -0.0005

Data Index: 283485 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0379. Min Act: -0.0005

Data Index: 476555 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0333. Min Act: -0.0005

Data Index: 1204497 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0380. Min Act: -0.0005

Data Index: 794360 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0310. Min Act: -0.0005

Data Index: 483380 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0306. Min Act: -0.0005

Data Index: 1052396 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0276. Min Act: -0.0005

Data Index: 859812 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0246. Min Act: -0.0005

Data Index: 436436 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0228. Min Act: -0.0005

Data Index: 1087984 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0236. Min Act: -0.0005

Data Index: 885645 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0236. Min Act: -0.0005

Data Index: 918505 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0244. Min Act: -0.0005

Data Index: 883162 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0226. Min Act: -0.0005

Data Index: 555009 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0236. Min Act: -0.0005

Data Index: 586426 (C4 (Web Text))

Max Activating Token Index: 342