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

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

Neuron 2515 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.4036. Min Act: -0.0000

Data Index: 667620 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.1685. Min Act: -0.0001

Data Index: 19529 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.1644. Min Act: -0.0000

Data Index: 144736 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.1557. Min Act: -0.0001

Data Index: 1280883 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.1774. Min Act: -0.0001

Data Index: 915793 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.1374. Min Act: -0.0001

Data Index: 465164 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.1383. Min Act: -0.0000

Data Index: 649184 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.0604. Min Act: -0.0001

Data Index: 333953 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.0508. Min Act: -0.0001

Data Index: 1248889 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.0437. Min Act: -0.0001

Data Index: 1042540 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.1023. Min Act: -0.0001

Data Index: 664404 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.0570. Min Act: -0.0001

Data Index: 30441 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.0626. Min Act: -0.0001

Data Index: 1039101 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.0252. Min Act: -0.0001

Data Index: 1608677 (Python Code)

Max Activating Token Index: 318

Text #14

Max Range: 1.4036. Min Range: -1.4036

Max Act: 0.9931. Min Act: -0.0001

Data Index: 1035707 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.0238. Min Act: -0.0001

Data Index: 1357586 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 1.4036. Min Range: -1.4036

Max Act: 0.9754. Min Act: -0.0001

Data Index: 337124 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.0052. Min Act: -0.0001

Data Index: 837183 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.0046. Min Act: -0.0000

Data Index: 124622 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 1.4036. Min Range: -1.4036

Max Act: 1.0027. Min Act: -0.0001

Data Index: 735664 (C4 (Web Text))

Max Activating Token Index: 126