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

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

Neuron 851 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: 0.0441. Min Range: -0.0441

Max Act: 0.0441. Min Act: -0.0002

Data Index: 93427 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0342. Min Act: -0.0002

Data Index: 645444 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0300. Min Act: -0.0003

Data Index: 41073 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1231227 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1056181 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1104424 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0303. Min Act: -0.0003

Data Index: 742071 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0302. Min Act: -0.0003

Data Index: 388849 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0309. Min Act: -0.0003

Data Index: 812405 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0286. Min Act: -0.0002

Data Index: 544142 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0289. Min Act: -0.0003

Data Index: 112377 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0283. Min Act: -0.0003

Data Index: 840750 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1313005 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0220. Min Act: -0.0003

Data Index: 855062 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1093411 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0281. Min Act: -0.0003

Data Index: 581035 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0272. Min Act: -0.0002

Data Index: 889432 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0251. Min Act: -0.0002

Data Index: 115486 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1570629 (Python Code)

Max Activating Token Index: 256

Text #19

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0263. Min Act: -0.0003

Data Index: 23143 (C4 (Web Text))

Max Activating Token Index: 259