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

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

Neuron 3300 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3712. Min Act: -0.0001

Data Index: 644900 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3832. Min Act: -0.0001

Data Index: 1073354 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3397. Min Act: -0.0001

Data Index: 651038 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3796. Min Act: -0.0001

Data Index: 905477 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3683. Min Act: -0.0001

Data Index: 825829 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3807. Min Act: -0.0001

Data Index: 51272 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3866. Min Act: -0.0001

Data Index: 350103 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3392. Min Act: -0.0001

Data Index: 1321191 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3465. Min Act: -0.0001

Data Index: 219732 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3654. Min Act: -0.0001

Data Index: 768880 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3978. Min Act: -0.0001

Data Index: 522608 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3660. Min Act: -0.0001

Data Index: 463379 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3945. Min Act: -0.0001

Data Index: 1148114 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3734. Min Act: -0.0001

Data Index: 485393 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3718. Min Act: -0.0001

Data Index: 471941 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3402. Min Act: -0.0001

Data Index: 161550 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3316. Min Act: -0.0001

Data Index: 899439 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3553. Min Act: -0.0001

Data Index: 1148664 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3483. Min Act: -0.0001

Data Index: 412229 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3469. Min Act: -0.0001

Data Index: 521751 (C4 (Web Text))

Max Activating Token Index: 787