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

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

Neuron 638 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: 0.0390. Min Range: -0.0390

Max Act: 0.0390. Min Act: -0.0006

Data Index: 96364 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0308. Min Act: -0.0006

Data Index: 100937 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0317. Min Act: -0.0006

Data Index: 332333 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0310. Min Act: -0.0006

Data Index: 405732 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1301079 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0321. Min Act: -0.0006

Data Index: 882709 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0291. Min Act: -0.0006

Data Index: 960162 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0307. Min Act: -0.0006

Data Index: 733698 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0282. Min Act: -0.0006

Data Index: 228008 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0280. Min Act: -0.0006

Data Index: 145768 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0244. Min Act: -0.0006

Data Index: 509183 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0280. Min Act: -0.0006

Data Index: 322160 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0276. Min Act: -0.0006

Data Index: 1315733 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0262. Min Act: -0.0006

Data Index: 440281 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0285. Min Act: -0.0006

Data Index: 1112294 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0288. Min Act: -0.0006

Data Index: 1179559 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0278. Min Act: -0.0006

Data Index: 195562 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0284. Min Act: -0.0006

Data Index: 1046576 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0253. Min Act: -0.0006

Data Index: 87036 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0267. Min Act: -0.0006

Data Index: 700554 (C4 (Web Text))

Max Activating Token Index: 941