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

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

Neuron 1757 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6883. Min Act: -0.0002

Data Index: 1286802 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.7013. Min Act: -0.0002

Data Index: 345241 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.7334. Min Act: -0.0002

Data Index: 278134 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6671. Min Act: -0.0002

Data Index: 1028499 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6553. Min Act: -0.0002

Data Index: 600395 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6183. Min Act: -0.0002

Data Index: 767527 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6138. Min Act: -0.0002

Data Index: 206867 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6551. Min Act: -0.0002

Data Index: 1262057 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5935. Min Act: -0.0002

Data Index: 888772 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6305. Min Act: -0.0002

Data Index: 1154163 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6040. Min Act: -0.0002

Data Index: 1084553 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6402. Min Act: -0.0002

Data Index: 410357 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6357. Min Act: -0.0002

Data Index: 54574 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5955. Min Act: -0.0002

Data Index: 1345929 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5651. Min Act: -0.0002

Data Index: 281864 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5880. Min Act: -0.0002

Data Index: 1357105 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6024. Min Act: -0.0002

Data Index: 685314 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5994. Min Act: -0.0002

Data Index: 1295764 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5994. Min Act: -0.0002

Data Index: 341212 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6183. Min Act: -0.0002

Data Index: 1125332 (C4 (Web Text))

Max Activating Token Index: 49