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

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

Neuron 928 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: 0.3612. Min Range: -0.3612

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1234465 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3525. Min Act: -0.0000

Data Index: 182635 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3612. Min Act: -0.0000

Data Index: 445900 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3555. Min Act: -0.0000

Data Index: 373162 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3363. Min Act: -0.0000

Data Index: 443696 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3478. Min Act: -0.0000

Data Index: 121825 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3111. Min Act: -0.0000

Data Index: 538555 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3056. Min Act: -0.0000

Data Index: 17134 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1046859 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3039. Min Act: -0.0000

Data Index: 339528 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2919. Min Act: -0.0000

Data Index: 588305 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3083. Min Act: -0.0000

Data Index: 777182 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2980. Min Act: -0.0000

Data Index: 947726 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1296182 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3027. Min Act: -0.0000

Data Index: 289967 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2873. Min Act: -0.0000

Data Index: 433533 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2978. Min Act: -0.0000

Data Index: 691777 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2816. Min Act: -0.0000

Data Index: 800666 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2767. Min Act: -0.0000

Data Index: 736986 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2851. Min Act: -0.0000

Data Index: 196218 (C4 (Web Text))

Max Activating Token Index: 920