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

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

Neuron 1462 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0349. Min Act: -0.0006

Data Index: 1356522 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0217. Min Act: -0.0006

Data Index: 314592 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0218. Min Act: -0.0006

Data Index: 31302 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0193. Min Act: -0.0006

Data Index: 313195 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0196. Min Act: -0.0006

Data Index: 637508 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0204. Min Act: -0.0006

Data Index: 814617 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0196. Min Act: -0.0006

Data Index: 770631 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0187. Min Act: -0.0006

Data Index: 786775 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0199. Min Act: -0.0006

Data Index: 340449 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0199. Min Act: -0.0006

Data Index: 1284152 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1344078 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0196. Min Act: -0.0006

Data Index: 237790 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0167. Min Act: -0.0006

Data Index: 744042 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0169. Min Act: -0.0006

Data Index: 585037 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0191. Min Act: -0.0006

Data Index: 764573 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0172. Min Act: -0.0006

Data Index: 202380 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1192348 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0186. Min Act: -0.0006

Data Index: 525444 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0172. Min Act: -0.0006

Data Index: 262228 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0180. Min Act: -0.0006

Data Index: 823665 (C4 (Web Text))

Max Activating Token Index: 736