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

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

Neuron 5275 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6207. Min Range: -2.6207

Max Act: 2.5713. Min Act: -0.0000

Data Index: 1248714 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 2.6207. Min Range: -2.6207

Max Act: 2.6207. Min Act: -0.0000

Data Index: 967169 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 2.6207. Min Range: -2.6207

Max Act: 2.2456. Min Act: -0.0000

Data Index: 505047 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 2.6207. Min Range: -2.6207

Max Act: 2.2097. Min Act: -0.0000

Data Index: 480442 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 2.6207. Min Range: -2.6207

Max Act: 2.0375. Min Act: -0.0000

Data Index: 21442 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 2.6207. Min Range: -2.6207

Max Act: 2.0146. Min Act: -0.0000

Data Index: 487703 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 2.6207. Min Range: -2.6207

Max Act: 2.1107. Min Act: -0.0000

Data Index: 620161 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 2.6207. Min Range: -2.6207

Max Act: 2.3116. Min Act: -0.0000

Data Index: 1164006 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 2.6207. Min Range: -2.6207

Max Act: 2.0509. Min Act: -0.0000

Data Index: 824630 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 2.6207. Min Range: -2.6207

Max Act: 1.8982. Min Act: -0.0000

Data Index: 52325 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 2.6207. Min Range: -2.6207

Max Act: 1.8877. Min Act: -0.0000

Data Index: 986623 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 2.6207. Min Range: -2.6207

Max Act: 1.9910. Min Act: -0.0000

Data Index: 348960 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 2.6207. Min Range: -2.6207

Max Act: 1.9299. Min Act: -0.0000

Data Index: 577257 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 2.6207. Min Range: -2.6207

Max Act: 1.9381. Min Act: -0.0000

Data Index: 475528 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 2.6207. Min Range: -2.6207

Max Act: 1.9288. Min Act: -0.0000

Data Index: 182880 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 2.6207. Min Range: -2.6207

Max Act: 2.0181. Min Act: -0.0000

Data Index: 575983 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 2.6207. Min Range: -2.6207

Max Act: 1.7928. Min Act: -0.0000

Data Index: 48896 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 2.6207. Min Range: -2.6207

Max Act: 1.8735. Min Act: -0.0000

Data Index: 626403 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 2.6207. Min Range: -2.6207

Max Act: 1.8659. Min Act: -0.0000

Data Index: 1123004 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 2.6207. Min Range: -2.6207

Max Act: 1.8847. Min Act: -0.0000

Data Index: 665025 (C4 (Web Text))

Max Activating Token Index: 903