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

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

Neuron 1764 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: 0.0206. Min Range: -0.0206

Max Act: 0.0205. Min Act: -0.0003

Data Index: 549570 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0206. Min Act: -0.0003

Data Index: 238334 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0197. Min Act: -0.0003

Data Index: 1289255 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0184. Min Act: -0.0003

Data Index: 188461 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0185. Min Act: -0.0002

Data Index: 83647 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0181. Min Act: -0.0003

Data Index: 578376 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0175. Min Act: -0.0003

Data Index: 38064 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0180. Min Act: -0.0003

Data Index: 888645 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0185. Min Act: -0.0003

Data Index: 924402 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0173. Min Act: -0.0003

Data Index: 262166 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0182. Min Act: -0.0003

Data Index: 981590 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0156. Min Act: -0.0003

Data Index: 49745 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1071840 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0160. Min Act: -0.0002

Data Index: 299197 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0160. Min Act: -0.0002

Data Index: 259543 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1208341 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0161. Min Act: -0.0003

Data Index: 347885 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1120229 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0162. Min Act: -0.0003

Data Index: 983837 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0166. Min Act: -0.0003

Data Index: 709889 (C4 (Web Text))

Max Activating Token Index: 681