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

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

Neuron 712 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.7518. Min Act: -0.0000

Data Index: 1124053 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.5342. Min Act: -0.0000

Data Index: 611642 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 4.7518. Min Range: -4.7518

Max Act: 3.7979. Min Act: -0.0000

Data Index: 327611 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 4.7518. Min Range: -4.7518

Max Act: 3.5430. Min Act: -0.0000

Data Index: 259666 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 4.7518. Min Range: -4.7518

Max Act: 3.4778. Min Act: -0.0000

Data Index: 1011638 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 4.7518. Min Range: -4.7518

Max Act: 3.6190. Min Act: -0.0000

Data Index: 739564 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 4.7518. Min Range: -4.7518

Max Act: 3.3621. Min Act: -0.0000

Data Index: 1170666 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 4.7518. Min Range: -4.7518

Max Act: 3.1968. Min Act: -0.0000

Data Index: 100611 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 4.7518. Min Range: -4.7518

Max Act: 3.3624. Min Act: -0.0000

Data Index: 1284794 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 4.7518. Min Range: -4.7518

Max Act: 3.3104. Min Act: -0.0000

Data Index: 884915 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 4.7518. Min Range: -4.7518

Max Act: 3.0397. Min Act: -0.0000

Data Index: 649440 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 4.7518. Min Range: -4.7518

Max Act: 2.8947. Min Act: -0.0000

Data Index: 987883 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 4.7518. Min Range: -4.7518

Max Act: 2.7165. Min Act: -0.0000

Data Index: 124648 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 4.7518. Min Range: -4.7518

Max Act: 2.7754. Min Act: -0.0000

Data Index: 1277520 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 4.7518. Min Range: -4.7518

Max Act: 2.7546. Min Act: -0.0000

Data Index: 400553 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 4.7518. Min Range: -4.7518

Max Act: 2.8614. Min Act: -0.0000

Data Index: 1345774 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 4.7518. Min Range: -4.7518

Max Act: 2.6920. Min Act: -0.0000

Data Index: 493776 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 4.7518. Min Range: -4.7518

Max Act: 2.6941. Min Act: -0.0000

Data Index: 652519 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 4.7518. Min Range: -4.7518

Max Act: 2.6075. Min Act: -0.0000

Data Index: 1054537 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 4.7518. Min Range: -4.7518

Max Act: 2.4527. Min Act: -0.0000

Data Index: 754703 (C4 (Web Text))

Max Activating Token Index: 924