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

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

Neuron 575 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2869. Min Act: -0.0001

Data Index: 1070508 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2615. Min Act: -0.0001

Data Index: 510108 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2393. Min Act: -0.0001

Data Index: 1320759 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2311. Min Act: -0.0001

Data Index: 1140755 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2240. Min Act: -0.0001

Data Index: 1119018 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2281. Min Act: -0.0001

Data Index: 706944 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2190. Min Act: -0.0001

Data Index: 1207702 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2389. Min Act: -0.0001

Data Index: 136843 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2237. Min Act: -0.0001

Data Index: 55019 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2361. Min Act: -0.0001

Data Index: 778655 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2110. Min Act: -0.0001

Data Index: 1159526 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2252. Min Act: -0.0001

Data Index: 867032 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2239. Min Act: -0.0001

Data Index: 1215900 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2076. Min Act: -0.0001

Data Index: 102370 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2123. Min Act: -0.0001

Data Index: 748989 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2172. Min Act: -0.0001

Data Index: 664812 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2208. Min Act: -0.0001

Data Index: 1228022 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2218. Min Act: -0.0001

Data Index: 562778 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2196. Min Act: -0.0001

Data Index: 1219836 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1920. Min Act: -0.0001

Data Index: 401880 (C4 (Web Text))

Max Activating Token Index: 55