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

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

Neuron 5372 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: 0.9679. Min Range: -0.9679

Max Act: 0.9606. Min Act: -0.0000

Data Index: 128824 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.9679. Min Act: -0.0000

Data Index: 577634 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.9196. Min Act: -0.0000

Data Index: 437930 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.8049. Min Act: -0.0000

Data Index: 317500 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1035720 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7600. Min Act: -0.0000

Data Index: 605181 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7274. Min Act: -0.0000

Data Index: 712386 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7321. Min Act: -0.0000

Data Index: 319318 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7282. Min Act: -0.0000

Data Index: 739453 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6725. Min Act: -0.0000

Data Index: 83449 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7147. Min Act: -0.0000

Data Index: 244828 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1218094 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7037. Min Act: -0.0000

Data Index: 602272 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6576. Min Act: -0.0000

Data Index: 471616 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1116674 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6999. Min Act: -0.0000

Data Index: 1193419 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1155701 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6403. Min Act: -0.0000

Data Index: 261555 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1039991 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1205601 (C4 (Web Text))

Max Activating Token Index: 374