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

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

Neuron 4111 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.3214. Min Act: -0.0000

Data Index: 68302 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.3216. Min Act: -0.0000

Data Index: 480095 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.3759. Min Act: -0.0000

Data Index: 1053218 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1823. Min Act: -0.0000

Data Index: 617138 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.2657. Min Act: -0.0000

Data Index: 365007 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.2226. Min Act: -0.0000

Data Index: 746775 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1830. Min Act: -0.0000

Data Index: 1133724 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1326. Min Act: -0.0000

Data Index: 517193 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1284. Min Act: -0.0000

Data Index: 843549 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0602. Min Act: -0.0000

Data Index: 854913 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0589. Min Act: -0.0000

Data Index: 69690 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1105. Min Act: -0.0000

Data Index: 263836 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0482. Min Act: -0.0000

Data Index: 786605 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1015. Min Act: -0.0000

Data Index: 262933 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0285. Min Act: -0.0000

Data Index: 1104432 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0324. Min Act: -0.0000

Data Index: 546557 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0586. Min Act: -0.0000

Data Index: 853606 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1019. Min Act: -0.0000

Data Index: 118609 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0560. Min Act: -0.0000

Data Index: 995426 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.9874. Min Act: -0.0000

Data Index: 727944 (C4 (Web Text))

Max Activating Token Index: 904