Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1832 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0292. Min Act: -0.0006

Data Index: 743508 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0282. Min Act: -0.0006

Data Index: 1321061 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0266. Min Act: -0.0006

Data Index: 1072 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0265. Min Act: -0.0006

Data Index: 813775 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0281. Min Act: -0.0006

Data Index: 721440 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0263. Min Act: -0.0006

Data Index: 923757 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0254. Min Act: -0.0006

Data Index: 752020 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0253. Min Act: -0.0006

Data Index: 263798 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0258. Min Act: -0.0006

Data Index: 613823 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0250. Min Act: -0.0006

Data Index: 474518 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0255. Min Act: -0.0006

Data Index: 196731 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0238. Min Act: -0.0006

Data Index: 151433 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1056741 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1117192 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0243. Min Act: -0.0006

Data Index: 330421 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0238. Min Act: -0.0006

Data Index: 603750 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0243. Min Act: -0.0006

Data Index: 841399 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1321847 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1201853 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0245. Min Act: -0.0006

Data Index: 539443 (C4 (Web Text))

Max Activating Token Index: 337