Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 442 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.6090. Min Act: -0.0001

Data Index: 704381 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.5516. Min Act: -0.0001

Data Index: 822142 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.5776. Min Act: -0.0001

Data Index: 106772 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.4075. Min Act: -0.0001

Data Index: 339537 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.4757. Min Act: -0.0002

Data Index: 886937 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.4254. Min Act: -0.0002

Data Index: 418412 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.4642. Min Act: -0.0002

Data Index: 677100 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.4008. Min Act: -0.0001

Data Index: 996587 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.3291. Min Act: -0.0002

Data Index: 304315 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.3978. Min Act: -0.0001

Data Index: 1321370 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.3038. Min Act: -0.0002

Data Index: 231867 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.3656. Min Act: -0.0002

Data Index: 312566 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.3512. Min Act: -0.0002

Data Index: 563456 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.3463. Min Act: -0.0002

Data Index: 372923 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.3357. Min Act: -0.0002

Data Index: 685973 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.3141. Min Act: -0.0002

Data Index: 536562 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.3514. Min Act: -0.0002

Data Index: 856996 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.3367. Min Act: -0.0001

Data Index: 430823 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.2719. Min Act: -0.0001

Data Index: 811639 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 1.6090. Min Range: -1.6090

Max Act: 1.3055. Min Act: -0.0002

Data Index: 167510 (C4 (Web Text))

Max Activating Token Index: 840