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

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

Neuron 779 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: 0.4039. Min Range: -0.4039

Max Act: 0.4039. Min Act: -0.0000

Data Index: 359112 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3511. Min Act: -0.0000

Data Index: 224858 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3539. Min Act: -0.0000

Data Index: 386287 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3331. Min Act: -0.0000

Data Index: 901321 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3447. Min Act: -0.0000

Data Index: 575335 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3337. Min Act: -0.0000

Data Index: 627743 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1315050 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3243. Min Act: -0.0000

Data Index: 146891 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3079. Min Act: -0.0000

Data Index: 850299 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2931. Min Act: -0.0000

Data Index: 71794 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1195151 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2827. Min Act: -0.0000

Data Index: 371354 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2869. Min Act: -0.0000

Data Index: 134934 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2928. Min Act: -0.0000

Data Index: 63191 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3068. Min Act: -0.0000

Data Index: 431879 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2960. Min Act: -0.0000

Data Index: 70950 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2770. Min Act: -0.0000

Data Index: 667808 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1074452 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1126245 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2709. Min Act: -0.0000

Data Index: 1051993 (C4 (Web Text))

Max Activating Token Index: 999