Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 211 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0201. Min Act: -0.0005

Data Index: 1316573 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0197. Min Act: -0.0005

Data Index: 420656 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0196. Min Act: -0.0005

Data Index: 131818 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0189. Min Act: -0.0005

Data Index: 145852 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0193. Min Act: -0.0005

Data Index: 788028 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0185. Min Act: -0.0005

Data Index: 118761 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0180. Min Act: -0.0005

Data Index: 21339 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0175. Min Act: -0.0005

Data Index: 262058 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0179. Min Act: -0.0005

Data Index: 1218832 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0179. Min Act: -0.0005

Data Index: 1365228 (Python Code)

Max Activating Token Index: 17

Text #10

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0178. Min Act: -0.0005

Data Index: 1247550 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0174. Min Act: -0.0006

Data Index: 917445 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0177. Min Act: -0.0005

Data Index: 396061 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0180. Min Act: -0.0005

Data Index: 1378874 (Python Code)

Max Activating Token Index: 888

Text #14

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0175. Min Act: -0.0005

Data Index: 378532 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0173. Min Act: -0.0005

Data Index: 132792 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0173. Min Act: -0.0005

Data Index: 926769 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0173. Min Act: -0.0005

Data Index: 496273 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0172. Min Act: -0.0005

Data Index: 659230 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0168. Min Act: -0.0005

Data Index: 476076 (C4 (Web Text))

Max Activating Token Index: 307