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

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

Neuron 250 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: 0.0282. Min Range: -0.0282

Max Act: 0.0273. Min Act: -0.0006

Data Index: 880445 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0282. Min Act: -0.0006

Data Index: 964890 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0277. Min Act: -0.0006

Data Index: 107350 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0264. Min Act: -0.0006

Data Index: 396048 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0266. Min Act: -0.0006

Data Index: 45267 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0252. Min Act: -0.0006

Data Index: 793004 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0255. Min Act: -0.0006

Data Index: 35896 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1057529 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0249. Min Act: -0.0006

Data Index: 964537 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0245. Min Act: -0.0006

Data Index: 847306 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1293124 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1352953 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0244. Min Act: -0.0006

Data Index: 262975 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0244. Min Act: -0.0006

Data Index: 38213 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0242. Min Act: -0.0006

Data Index: 524102 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0242. Min Act: -0.0006

Data Index: 6800 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0240. Min Act: -0.0006

Data Index: 867835 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0228. Min Act: -0.0006

Data Index: 1100932 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0235. Min Act: -0.0006

Data Index: 459614 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0234. Min Act: -0.0006

Data Index: 295814 (C4 (Web Text))

Max Activating Token Index: 990