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

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

Neuron 153 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: 6.3208. Min Range: -6.3208

Max Act: 6.3208. Min Act: -0.0000

Data Index: 254975 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 6.3208. Min Range: -6.3208

Max Act: 6.0542. Min Act: -0.0000

Data Index: 1340044 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 6.3208. Min Range: -6.3208

Max Act: 5.8374. Min Act: -0.0000

Data Index: 361886 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 6.3208. Min Range: -6.3208

Max Act: 5.8393. Min Act: -0.0000

Data Index: 763708 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 6.3208. Min Range: -6.3208

Max Act: 5.5417. Min Act: -0.0000

Data Index: 760584 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 6.3208. Min Range: -6.3208

Max Act: 5.4886. Min Act: -0.0000

Data Index: 1101917 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 6.3208. Min Range: -6.3208

Max Act: 5.5779. Min Act: -0.0000

Data Index: 590687 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 6.3208. Min Range: -6.3208

Max Act: 5.5736. Min Act: -0.0000

Data Index: 252235 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 6.3208. Min Range: -6.3208

Max Act: 5.3190. Min Act: -0.0000

Data Index: 787651 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 6.3208. Min Range: -6.3208

Max Act: 5.2745. Min Act: -0.0000

Data Index: 1270368 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 6.3208. Min Range: -6.3208

Max Act: 4.9885. Min Act: -0.0000

Data Index: 518561 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 6.3208. Min Range: -6.3208

Max Act: 4.9869. Min Act: -0.0000

Data Index: 1158801 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 6.3208. Min Range: -6.3208

Max Act: 4.7961. Min Act: -0.0000

Data Index: 158855 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 6.3208. Min Range: -6.3208

Max Act: 5.1023. Min Act: -0.0000

Data Index: 863908 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 6.3208. Min Range: -6.3208

Max Act: 5.2535. Min Act: -0.0000

Data Index: 409273 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 6.3208. Min Range: -6.3208

Max Act: 5.0251. Min Act: -0.0000

Data Index: 1348570 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 6.3208. Min Range: -6.3208

Max Act: 4.9645. Min Act: -0.0000

Data Index: 1224218 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 6.3208. Min Range: -6.3208

Max Act: 4.7605. Min Act: -0.0000

Data Index: 352955 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 6.3208. Min Range: -6.3208

Max Act: 4.9573. Min Act: -0.0000

Data Index: 947329 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 6.3208. Min Range: -6.3208

Max Act: 4.8794. Min Act: -0.0000

Data Index: 866410 (C4 (Web Text))

Max Activating Token Index: 171