Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2253 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.6281. Min Act: -0.0001

Data Index: 496779 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5889. Min Act: -0.0001

Data Index: 1093886 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5359. Min Act: -0.0001

Data Index: 1270889 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5082. Min Act: -0.0001

Data Index: 1262879 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5350. Min Act: -0.0001

Data Index: 292222 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5104. Min Act: -0.0001

Data Index: 1018695 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4471. Min Act: -0.0001

Data Index: 1114857 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4230. Min Act: -0.0001

Data Index: 461874 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4333. Min Act: -0.0001

Data Index: 731552 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4400. Min Act: -0.0001

Data Index: 701879 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4344. Min Act: -0.0001

Data Index: 938609 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4321. Min Act: -0.0001

Data Index: 1216860 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4297. Min Act: -0.0001

Data Index: 582212 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4388. Min Act: -0.0001

Data Index: 960266 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4246. Min Act: -0.0001

Data Index: 603901 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.3920. Min Act: -0.0001

Data Index: 116746 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4361. Min Act: -0.0001

Data Index: 686493 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.3917. Min Act: -0.0001

Data Index: 688154 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4195. Min Act: -0.0001

Data Index: 1036864 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4318. Min Act: -0.0001

Data Index: 1061421 (C4 (Web Text))

Max Activating Token Index: 849