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

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

Neuron 2051 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7796. Min Range: -1.7796

Max Act: 1.7796. Min Act: -0.0000

Data Index: 388734 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 1.7796. Min Range: -1.7796

Max Act: 1.4406. Min Act: -0.0000

Data Index: 486041 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 1.7796. Min Range: -1.7796

Max Act: 1.2334. Min Act: -0.0000

Data Index: 720292 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 1.7796. Min Range: -1.7796

Max Act: 1.2010. Min Act: -0.0000

Data Index: 133612 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 1.7796. Min Range: -1.7796

Max Act: 1.1279. Min Act: -0.0000

Data Index: 1329393 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 1.7796. Min Range: -1.7796

Max Act: 1.1120. Min Act: -0.0000

Data Index: 165608 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 1.7796. Min Range: -1.7796

Max Act: 1.1260. Min Act: -0.0000

Data Index: 274820 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 1.7796. Min Range: -1.7796

Max Act: 1.0966. Min Act: -0.0000

Data Index: 738529 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 1.7796. Min Range: -1.7796

Max Act: 0.9888. Min Act: -0.0000

Data Index: 913868 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 1.7796. Min Range: -1.7796

Max Act: 1.0129. Min Act: -0.0000

Data Index: 255098 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 1.7796. Min Range: -1.7796

Max Act: 1.0297. Min Act: -0.0000

Data Index: 91397 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 1.7796. Min Range: -1.7796

Max Act: 1.0296. Min Act: -0.0000

Data Index: 862376 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 1.7796. Min Range: -1.7796

Max Act: 0.9850. Min Act: -0.0000

Data Index: 784198 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 1.7796. Min Range: -1.7796

Max Act: 1.0446. Min Act: -0.0000

Data Index: 774721 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 1.7796. Min Range: -1.7796

Max Act: 0.9627. Min Act: -0.0000

Data Index: 823224 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 1.7796. Min Range: -1.7796

Max Act: 0.9840. Min Act: -0.0000

Data Index: 917117 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 1.7796. Min Range: -1.7796

Max Act: 0.9524. Min Act: -0.0000

Data Index: 426752 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 1.7796. Min Range: -1.7796

Max Act: 0.9955. Min Act: -0.0000

Data Index: 406256 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 1.7796. Min Range: -1.7796

Max Act: 0.9450. Min Act: -0.0000

Data Index: 422687 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 1.7796. Min Range: -1.7796

Max Act: 0.9617. Min Act: -0.0000

Data Index: 345525 (C4 (Web Text))

Max Activating Token Index: 293