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

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

Neuron 3754 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1184. Min Range: -1.1184

Max Act: 1.1184. Min Act: -0.0000

Data Index: 46967 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9959. Min Act: -0.0000

Data Index: 36200 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.8929. Min Act: -0.0000

Data Index: 587280 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.8687. Min Act: -0.0000

Data Index: 263541 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.8200. Min Act: -0.0000

Data Index: 146051 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.7870. Min Act: -0.0000

Data Index: 1029317 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.7311. Min Act: -0.0000

Data Index: 1259789 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.7265. Min Act: -0.0000

Data Index: 462512 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1357570 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.7233. Min Act: -0.0001

Data Index: 673995 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.7207. Min Act: -0.0000

Data Index: 640018 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6727. Min Act: -0.0000

Data Index: 324657 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6580. Min Act: -0.0000

Data Index: 130502 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6862. Min Act: -0.0000

Data Index: 469892 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1142831 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1379748 (Python Code)

Max Activating Token Index: 830

Text #16

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6191. Min Act: -0.0000

Data Index: 502350 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1253988 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.6671. Min Act: -0.0000

Data Index: 587756 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.4694. Min Act: -0.0000

Data Index: 792398 (C4 (Web Text))

Max Activating Token Index: 993