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

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

Neuron 3684 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: 0.0300. Min Range: -0.0300

Max Act: 0.0300. Min Act: -0.0001

Data Index: 813530 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0257. Min Act: -0.0001

Data Index: 349920 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0231. Min Act: -0.0001

Data Index: 562530 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0205. Min Act: -0.0001

Data Index: 467804 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0190. Min Act: -0.0001

Data Index: 969893 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0188. Min Act: -0.0001

Data Index: 1212428 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0201. Min Act: -0.0001

Data Index: 398875 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0175. Min Act: -0.0001

Data Index: 1127975 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0184. Min Act: -0.0001

Data Index: 1424063 (Python Code)

Max Activating Token Index: 369

Text #9

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0148. Min Act: -0.0001

Data Index: 1211440 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0195. Min Act: -0.0001

Data Index: 1408001 (Python Code)

Max Activating Token Index: 86

Text #11

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0161. Min Act: -0.0001

Data Index: 1332932 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0175. Min Act: -0.0001

Data Index: 942421 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0172. Min Act: -0.0001

Data Index: 391173 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0171. Min Act: -0.0001

Data Index: 1269312 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1062017 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0183. Min Act: -0.0001

Data Index: 631044 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0158. Min Act: -0.0001

Data Index: 710340 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0156. Min Act: -0.0001

Data Index: 621936 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0171. Min Act: -0.0001

Data Index: 983495 (C4 (Web Text))

Max Activating Token Index: 333