Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3234 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.3049. Min Act: -0.0001

Data Index: 753340 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2745. Min Act: -0.0001

Data Index: 1143520 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2748. Min Act: -0.0001

Data Index: 1315863 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2614. Min Act: -0.0001

Data Index: 267032 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2639. Min Act: -0.0001

Data Index: 1159398 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2549. Min Act: -0.0001

Data Index: 1094576 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2308. Min Act: -0.0001

Data Index: 232928 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2523. Min Act: -0.0001

Data Index: 892711 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2301. Min Act: -0.0001

Data Index: 166479 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2192. Min Act: -0.0001

Data Index: 658180 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2105. Min Act: -0.0001

Data Index: 608473 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2232. Min Act: -0.0001

Data Index: 483420 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2068. Min Act: -0.0001

Data Index: 49848 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2128. Min Act: -0.0001

Data Index: 983663 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2199. Min Act: -0.0001

Data Index: 1136214 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2114. Min Act: -0.0001

Data Index: 1353194 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2116. Min Act: -0.0001

Data Index: 105462 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.1952. Min Act: -0.0001

Data Index: 694895 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.2150. Min Act: -0.0001

Data Index: 78524 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.3049. Min Range: -0.3049

Max Act: 0.1831. Min Act: -0.0001

Data Index: 825554 (C4 (Web Text))

Max Activating Token Index: 781