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

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

Neuron 1684 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0270. Min Act: -0.0006

Data Index: 16850 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0261. Min Act: -0.0006

Data Index: 284885 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1289357 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0255. Min Act: -0.0006

Data Index: 991888 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0252. Min Act: -0.0006

Data Index: 856650 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1344872 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0238. Min Act: -0.0006

Data Index: 969828 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0231. Min Act: -0.0006

Data Index: 437631 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0235. Min Act: -0.0006

Data Index: 375014 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0235. Min Act: -0.0006

Data Index: 907393 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0233. Min Act: -0.0006

Data Index: 818526 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1244612 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1343282 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0232. Min Act: -0.0006

Data Index: 600982 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0226. Min Act: -0.0006

Data Index: 778517 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0225. Min Act: -0.0006

Data Index: 934950 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1278888 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0223. Min Act: -0.0006

Data Index: 771481 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0224. Min Act: -0.0006

Data Index: 980817 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0219. Min Act: -0.0006

Data Index: 369942 (C4 (Web Text))

Max Activating Token Index: 630