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

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

Neuron 1515 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0041. Min Range: -2.0041

Max Act: 2.0041. Min Act: -0.0000

Data Index: 1354974 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.6704. Min Act: -0.0000

Data Index: 1566104 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.4411. Min Act: -0.0000

Data Index: 413420 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.6208. Min Act: -0.0000

Data Index: 673609 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.4255. Min Act: -0.0000

Data Index: 1007079 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.4158. Min Act: -0.0000

Data Index: 206160 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.3202. Min Act: -0.0000

Data Index: 453690 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.3781. Min Act: -0.0000

Data Index: 40484 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.3022. Min Act: -0.0000

Data Index: 979706 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.3224. Min Act: -0.0000

Data Index: 65967 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.3040. Min Act: -0.0000

Data Index: 1034662 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.1857. Min Act: -0.0000

Data Index: 39699 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.3026. Min Act: -0.0000

Data Index: 814568 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.2998. Min Act: -0.0000

Data Index: 1516949 (Python Code)

Max Activating Token Index: 69

Text #14

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.2265. Min Act: -0.0000

Data Index: 1246182 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.3507. Min Act: -0.0000

Data Index: 1239816 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.2840. Min Act: -0.0000

Data Index: 653844 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.2043. Min Act: -0.0000

Data Index: 198994 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.2435. Min Act: -0.0000

Data Index: 886938 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.2268. Min Act: -0.0000

Data Index: 788065 (C4 (Web Text))

Max Activating Token Index: 476