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

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

Neuron 4379 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: 1.5533. Min Range: -1.5533

Max Act: 1.5533. Min Act: -0.0000

Data Index: 878486 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 1.5533. Min Range: -1.5533

Max Act: 1.3348. Min Act: -0.0000

Data Index: 421340 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 1.5533. Min Range: -1.5533

Max Act: 1.4149. Min Act: -0.0000

Data Index: 1027827 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 1.5533. Min Range: -1.5533

Max Act: 1.3330. Min Act: -0.0000

Data Index: 854099 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 1.5533. Min Range: -1.5533

Max Act: 1.1726. Min Act: -0.0000

Data Index: 391959 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 1.5533. Min Range: -1.5533

Max Act: 1.2164. Min Act: -0.0000

Data Index: 1115625 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 1.5533. Min Range: -1.5533

Max Act: 1.1065. Min Act: -0.0000

Data Index: 91942 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 1.5533. Min Range: -1.5533

Max Act: 1.0907. Min Act: -0.0000

Data Index: 988385 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 1.5533. Min Range: -1.5533

Max Act: 1.0916. Min Act: -0.0000

Data Index: 357211 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 1.5533. Min Range: -1.5533

Max Act: 1.0830. Min Act: -0.0000

Data Index: 41990 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 1.5533. Min Range: -1.5533

Max Act: 1.1316. Min Act: -0.0000

Data Index: 953410 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 1.5533. Min Range: -1.5533

Max Act: 1.0451. Min Act: -0.0000

Data Index: 1053404 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 1.5533. Min Range: -1.5533

Max Act: 1.0379. Min Act: -0.0000

Data Index: 446958 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 1.5533. Min Range: -1.5533

Max Act: 0.9954. Min Act: -0.0000

Data Index: 822048 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 1.5533. Min Range: -1.5533

Max Act: 0.9942. Min Act: -0.0000

Data Index: 66975 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 1.5533. Min Range: -1.5533

Max Act: 0.9967. Min Act: -0.0000

Data Index: 780593 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 1.5533. Min Range: -1.5533

Max Act: 0.9890. Min Act: -0.0000

Data Index: 1330769 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 1.5533. Min Range: -1.5533

Max Act: 1.0412. Min Act: -0.0000

Data Index: 330263 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 1.5533. Min Range: -1.5533

Max Act: 0.9178. Min Act: -0.0000

Data Index: 683818 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.5533. Min Range: -1.5533

Max Act: 0.9665. Min Act: -0.0000

Data Index: 533304 (C4 (Web Text))

Max Activating Token Index: 255