Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4375 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0627. Min Act: -0.0002

Data Index: 664517 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0624. Min Act: -0.0002

Data Index: 958032 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1259790 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0634. Min Act: -0.0002

Data Index: 850153 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0525. Min Act: -0.0002

Data Index: 325985 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1031230 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0573. Min Act: -0.0002

Data Index: 839695 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1259132 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0550. Min Act: -0.0002

Data Index: 720329 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1475502 (Python Code)

Max Activating Token Index: 108

Text #10

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0560. Min Act: -0.0002

Data Index: 821187 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0580. Min Act: -0.0002

Data Index: 322855 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0515. Min Act: -0.0002

Data Index: 761022 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0555. Min Act: -0.0002

Data Index: 948785 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0537. Min Act: -0.0002

Data Index: 749248 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0539. Min Act: -0.0002

Data Index: 12556 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0530. Min Act: -0.0002

Data Index: 192512 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1494149 (Python Code)

Max Activating Token Index: 228

Text #18

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0513. Min Act: -0.0002

Data Index: 171407 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1321175 (C4 (Web Text))

Max Activating Token Index: 351