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

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

Neuron 4472 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: 1.3151. Min Range: -1.3151

Max Act: 1.3151. Min Act: -0.0000

Data Index: 96025 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.2047. Min Act: -0.0000

Data Index: 1138645 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.1340. Min Act: -0.0000

Data Index: 89414 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.0080. Min Act: -0.0000

Data Index: 322148 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.0326. Min Act: -0.0000

Data Index: 1085275 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.9762. Min Act: -0.0000

Data Index: 280474 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.9502. Min Act: -0.0000

Data Index: 590943 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.9291. Min Act: -0.0000

Data Index: 110254 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.9511. Min Act: -0.0000

Data Index: 149950 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1014349 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1349186 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8962. Min Act: -0.0000

Data Index: 846899 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8614. Min Act: -0.0000

Data Index: 497503 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8860. Min Act: -0.0000

Data Index: 980209 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8128. Min Act: -0.0000

Data Index: 644984 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8584. Min Act: -0.0000

Data Index: 11648 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1123258 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.7783. Min Act: -0.0000

Data Index: 516369 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1061754 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8511. Min Act: -0.0000

Data Index: 990759 (C4 (Web Text))

Max Activating Token Index: 596