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

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

Neuron 2758 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2744. Min Range: -3.2744

Max Act: 3.2744. Min Act: -0.0000

Data Index: 1311299 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 3.2744. Min Range: -3.2744

Max Act: 3.2431. Min Act: -0.0000

Data Index: 147268 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 3.2744. Min Range: -3.2744

Max Act: 3.1869. Min Act: -0.0000

Data Index: 837660 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 3.2744. Min Range: -3.2744

Max Act: 3.0188. Min Act: -0.0000

Data Index: 474791 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 3.2744. Min Range: -3.2744

Max Act: 2.9526. Min Act: -0.0000

Data Index: 849529 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 3.2744. Min Range: -3.2744

Max Act: 2.6952. Min Act: -0.0000

Data Index: 940508 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 3.2744. Min Range: -3.2744

Max Act: 3.1187. Min Act: -0.0000

Data Index: 724417 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 3.2744. Min Range: -3.2744

Max Act: 2.3054. Min Act: -0.0000

Data Index: 311053 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 3.2744. Min Range: -3.2744

Max Act: 2.0794. Min Act: -0.0000

Data Index: 348676 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 3.2744. Min Range: -3.2744

Max Act: 2.0437. Min Act: -0.0000

Data Index: 1358641 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.9264. Min Act: -0.0000

Data Index: 529834 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.9685. Min Act: -0.0000

Data Index: 1224593 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.8282. Min Act: -0.0000

Data Index: 227639 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.8934. Min Act: 0.0000

Data Index: 659890 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.8854. Min Act: -0.0000

Data Index: 965516 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.8340. Min Act: -0.0000

Data Index: 1202028 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.7486. Min Act: -0.0000

Data Index: 166301 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.7436. Min Act: 0.0001

Data Index: 704269 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.7803. Min Act: -0.0000

Data Index: 1294361 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.6414. Min Act: -0.0000

Data Index: 68793 (C4 (Web Text))

Max Activating Token Index: 97