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

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

Neuron 1288 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: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0006

Data Index: 1151144 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0277. Min Act: -0.0006

Data Index: 349200 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0261. Min Act: -0.0006

Data Index: 710253 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0261. Min Act: -0.0006

Data Index: 1291392 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0260. Min Act: -0.0006

Data Index: 537127 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0261. Min Act: -0.0006

Data Index: 533865 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0265. Min Act: -0.0006

Data Index: 520166 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0238. Min Act: -0.0006

Data Index: 622428 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0248. Min Act: -0.0006

Data Index: 771306 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0245. Min Act: -0.0006

Data Index: 227399 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0230. Min Act: -0.0006

Data Index: 898858 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0243. Min Act: -0.0006

Data Index: 220848 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1312790 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0248. Min Act: -0.0006

Data Index: 394995 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0241. Min Act: -0.0006

Data Index: 127134 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0235. Min Act: -0.0006

Data Index: 661726 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1001901 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0225. Min Act: -0.0006

Data Index: 643579 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0252. Min Act: -0.0006

Data Index: 681556 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0233. Min Act: -0.0006

Data Index: 49808 (C4 (Web Text))

Max Activating Token Index: 832