Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3536 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2549. Min Range: -1.2549

Max Act: 1.1404. Min Act: -0.0000

Data Index: 282347 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 1.2549. Min Range: -1.2549

Max Act: 1.2549. Min Act: -0.0000

Data Index: 163013 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 1.2549. Min Range: -1.2549

Max Act: 1.1905. Min Act: -0.0000

Data Index: 866732 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 1.2549. Min Range: -1.2549

Max Act: 1.0480. Min Act: -0.0000

Data Index: 671717 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 1.2549. Min Range: -1.2549

Max Act: 1.0008. Min Act: -0.0000

Data Index: 135422 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 1.2549. Min Range: -1.2549

Max Act: 0.9176. Min Act: -0.0000

Data Index: 1111757 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 1.2549. Min Range: -1.2549

Max Act: 1.0226. Min Act: -0.0000

Data Index: 141319 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 1.2549. Min Range: -1.2549

Max Act: 1.0083. Min Act: -0.0000

Data Index: 931692 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 1.2549. Min Range: -1.2549

Max Act: 1.0037. Min Act: -0.0000

Data Index: 280335 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 1.2549. Min Range: -1.2549

Max Act: 0.8595. Min Act: -0.0000

Data Index: 672475 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 1.2549. Min Range: -1.2549

Max Act: 0.9230. Min Act: -0.0000

Data Index: 570079 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 1.2549. Min Range: -1.2549

Max Act: 0.8778. Min Act: -0.0000

Data Index: 953711 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 1.2549. Min Range: -1.2549

Max Act: 0.8773. Min Act: -0.0000

Data Index: 951974 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 1.2549. Min Range: -1.2549

Max Act: 0.8519. Min Act: -0.0000

Data Index: 141835 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 1.2549. Min Range: -1.2549

Max Act: 0.8041. Min Act: -0.0000

Data Index: 455272 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 1.2549. Min Range: -1.2549

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1228674 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 1.2549. Min Range: -1.2549

Max Act: 0.7881. Min Act: -0.0000

Data Index: 1070229 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 1.2549. Min Range: -1.2549

Max Act: 0.7200. Min Act: -0.0000

Data Index: 7952 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 1.2549. Min Range: -1.2549

Max Act: 0.6903. Min Act: -0.0000

Data Index: 818218 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 1.2549. Min Range: -1.2549

Max Act: 0.6507. Min Act: -0.0000

Data Index: 546466 (C4 (Web Text))

Max Activating Token Index: 535