Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3582 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1096852 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0280. Min Act: -0.0002

Data Index: 433115 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0269. Min Act: -0.0002

Data Index: 356126 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0263. Min Act: -0.0002

Data Index: 913008 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0280. Min Act: -0.0002

Data Index: 839888 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1280617 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1272845 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1222940 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1337423 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0246. Min Act: -0.0002

Data Index: 85558 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0249. Min Act: -0.0002

Data Index: 555270 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0249. Min Act: -0.0002

Data Index: 260906 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0239. Min Act: -0.0002

Data Index: 92560 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0244. Min Act: -0.0002

Data Index: 1611733 (Python Code)

Max Activating Token Index: 620

Text #14

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0236. Min Act: -0.0002

Data Index: 855978 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1384800 (Python Code)

Max Activating Token Index: 504

Text #16

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1622748 (Python Code)

Max Activating Token Index: 24

Text #17

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0230. Min Act: -0.0002

Data Index: 195398 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1107806 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1512599 (Python Code)

Max Activating Token Index: 277