Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1028 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0323. Min Act: -0.0003

Data Index: 261153 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0328. Min Act: -0.0003

Data Index: 331664 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0312. Min Act: -0.0003

Data Index: 276701 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0315. Min Act: -0.0003

Data Index: 282474 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1578122 (Python Code)

Max Activating Token Index: 194

Text #5

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0292. Min Act: -0.0003

Data Index: 458897 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1178782 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1178989 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0272. Min Act: -0.0003

Data Index: 337771 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0261. Min Act: -0.0003

Data Index: 415844 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0261. Min Act: -0.0003

Data Index: 405287 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0261. Min Act: -0.0003

Data Index: 321906 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1096995 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0265. Min Act: -0.0003

Data Index: 985973 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1621311 (Python Code)

Max Activating Token Index: 113

Text #15

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0253. Min Act: -0.0004

Data Index: 1048189 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0246. Min Act: -0.0003

Data Index: 966412 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1175811 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0247. Min Act: -0.0003

Data Index: 402114 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0242. Min Act: -0.0003

Data Index: 915380 (C4 (Web Text))

Max Activating Token Index: 773