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

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

Neuron 3302 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0002

Data Index: 999732 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0271. Min Act: -0.0002

Data Index: 23044 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0265. Min Act: -0.0002

Data Index: 517669 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0230. Min Act: -0.0002

Data Index: 85251 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0256. Min Act: -0.0002

Data Index: 923995 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0249. Min Act: -0.0002

Data Index: 905806 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0238. Min Act: -0.0002

Data Index: 631499 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1156263 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0246. Min Act: -0.0002

Data Index: 468950 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0253. Min Act: -0.0002

Data Index: 50277 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0227. Min Act: -0.0002

Data Index: 200613 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1160947 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0222. Min Act: -0.0002

Data Index: 341300 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0220. Min Act: -0.0002

Data Index: 442360 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0231. Min Act: -0.0002

Data Index: 968009 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0222. Min Act: -0.0002

Data Index: 436962 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0205. Min Act: -0.0002

Data Index: 15265 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0226. Min Act: -0.0002

Data Index: 26189 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0217. Min Act: -0.0002

Data Index: 863451 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0232. Min Act: -0.0002

Data Index: 274467 (C4 (Web Text))

Max Activating Token Index: 662