Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 636 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0316. Min Range: -2.0316

Max Act: 2.0316. Min Act: -0.0000

Data Index: 131511 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.7569. Min Act: -0.0000

Data Index: 1012509 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.8358. Min Act: -0.0000

Data Index: 1308620 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.6801. Min Act: -0.0000

Data Index: 1186400 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.5950. Min Act: -0.0000

Data Index: 166347 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.5527. Min Act: -0.0000

Data Index: 627702 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.5372. Min Act: -0.0000

Data Index: 1005754 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.5928. Min Act: -0.0000

Data Index: 158682 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.4790. Min Act: -0.0000

Data Index: 60410 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.6428. Min Act: -0.0000

Data Index: 1237480 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.7355. Min Act: -0.0000

Data Index: 1185244 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.5723. Min Act: -0.0000

Data Index: 158468 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.6398. Min Act: -0.0000

Data Index: 689232 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.6397. Min Act: -0.0000

Data Index: 1165195 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.5984. Min Act: -0.0000

Data Index: 717073 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.3455. Min Act: -0.0000

Data Index: 731193 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.6098. Min Act: -0.0000

Data Index: 1054025 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.6210. Min Act: -0.0000

Data Index: 566043 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.5168. Min Act: -0.0000

Data Index: 1070388 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 2.0316. Min Range: -2.0316

Max Act: 1.5387. Min Act: -0.0000

Data Index: 790160 (C4 (Web Text))

Max Activating Token Index: 936