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

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

Neuron 4607 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1363. Min Act: -0.0003

Data Index: 321567 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1350. Min Act: -0.0002

Data Index: 892684 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1288. Min Act: -0.0002

Data Index: 1341609 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1194. Min Act: -0.0002

Data Index: 47963 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1183. Min Act: -0.0002

Data Index: 3162 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1043. Min Act: -0.0002

Data Index: 394373 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0999. Min Act: -0.0002

Data Index: 655181 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1075. Min Act: -0.0003

Data Index: 412080 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0950. Min Act: -0.0002

Data Index: 1180410 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1042. Min Act: -0.0002

Data Index: 424264 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1000. Min Act: -0.0003

Data Index: 1006903 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0962. Min Act: -0.0002

Data Index: 943705 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0979. Min Act: -0.0002

Data Index: 670261 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0954. Min Act: -0.0003

Data Index: 522709 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0990. Min Act: -0.0003

Data Index: 815908 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0941. Min Act: -0.0002

Data Index: 451710 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0905. Min Act: -0.0002

Data Index: 208023 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0885. Min Act: -0.0003

Data Index: 1056995 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0856. Min Act: -0.0002

Data Index: 553211 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0901. Min Act: -0.0003

Data Index: 1280694 (C4 (Web Text))

Max Activating Token Index: 137