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

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

Neuron 4458 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2371. Min Range: -1.2371

Max Act: 1.2371. Min Act: -0.0000

Data Index: 770351 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 1.2371. Min Range: -1.2371

Max Act: 1.1513. Min Act: -0.0000

Data Index: 805062 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 1.2371. Min Range: -1.2371

Max Act: 1.1433. Min Act: -0.0000

Data Index: 1254152 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 1.2371. Min Range: -1.2371

Max Act: 1.0544. Min Act: -0.0000

Data Index: 1226368 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.9769. Min Act: -0.0000

Data Index: 785913 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 1.2371. Min Range: -1.2371

Max Act: 1.0120. Min Act: -0.0000

Data Index: 537457 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 1.2371. Min Range: -1.2371

Max Act: 1.0815. Min Act: -0.0000

Data Index: 745485 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.9697. Min Act: -0.0000

Data Index: 482201 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.9765. Min Act: -0.0000

Data Index: 152064 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1340775 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.9405. Min Act: -0.0000

Data Index: 1008854 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.9352. Min Act: -0.0000

Data Index: 147573 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1138986 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8326. Min Act: -0.0000

Data Index: 163095 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8159. Min Act: -0.0000

Data Index: 636839 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8564. Min Act: -0.0000

Data Index: 288734 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8072. Min Act: -0.0000

Data Index: 877535 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1355674 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.7774. Min Act: -0.0000

Data Index: 111858 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.7879. Min Act: -0.0000

Data Index: 369915 (C4 (Web Text))

Max Activating Token Index: 253