Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4093 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1184502 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0495. Min Act: -0.0003

Data Index: 258610 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1052692 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0472. Min Act: -0.0003

Data Index: 1229548 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0415. Min Act: -0.0003

Data Index: 339830 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1068478 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0417. Min Act: -0.0003

Data Index: 609048 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0436. Min Act: -0.0003

Data Index: 578310 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0406. Min Act: -0.0003

Data Index: 1308038 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0404. Min Act: -0.0003

Data Index: 689930 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0397. Min Act: -0.0003

Data Index: 325033 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0387. Min Act: -0.0003

Data Index: 705246 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0380. Min Act: -0.0002

Data Index: 836805 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0417. Min Act: -0.0003

Data Index: 812321 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0378. Min Act: -0.0003

Data Index: 406245 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0375. Min Act: -0.0003

Data Index: 463832 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0358. Min Act: -0.0003

Data Index: 122147 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0360. Min Act: -0.0003

Data Index: 598560 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0375. Min Act: -0.0003

Data Index: 372264 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1294207 (C4 (Web Text))

Max Activating Token Index: 35