Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 953 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0227. Min Act: -0.0006

Data Index: 339502 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0223. Min Act: -0.0006

Data Index: 894061 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1105288 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0213. Min Act: -0.0006

Data Index: 857748 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0207. Min Act: -0.0006

Data Index: 863636 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0200. Min Act: -0.0006

Data Index: 1278066 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0204. Min Act: -0.0006

Data Index: 586397 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0208. Min Act: -0.0006

Data Index: 934581 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0201. Min Act: -0.0006

Data Index: 1030389 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0199. Min Act: -0.0006

Data Index: 355046 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0202. Min Act: -0.0006

Data Index: 1470248 (Python Code)

Max Activating Token Index: 355

Text #11

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0202. Min Act: -0.0006

Data Index: 1257910 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0192. Min Act: -0.0006

Data Index: 938400 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0200. Min Act: -0.0006

Data Index: 456130 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1549971 (Python Code)

Max Activating Token Index: 361

Text #15

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0195. Min Act: -0.0006

Data Index: 1528607 (Python Code)

Max Activating Token Index: 995

Text #16

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0190. Min Act: -0.0006

Data Index: 849021 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0190. Min Act: -0.0006

Data Index: 630058 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0194. Min Act: -0.0006

Data Index: 354920 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0197. Min Act: -0.0006

Data Index: 33014 (C4 (Web Text))

Max Activating Token Index: 529