Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2004 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0668. Min Act: -0.0006

Data Index: 459411 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0632. Min Act: -0.0006

Data Index: 173342 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0588. Min Act: -0.0006

Data Index: 1243306 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0576. Min Act: -0.0006

Data Index: 334330 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0574. Min Act: -0.0005

Data Index: 1333642 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0584. Min Act: -0.0006

Data Index: 250372 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0575. Min Act: -0.0006

Data Index: 642111 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0583. Min Act: -0.0006

Data Index: 843077 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0584. Min Act: -0.0006

Data Index: 1305340 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0570. Min Act: -0.0006

Data Index: 322497 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0594. Min Act: -0.0006

Data Index: 526874 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0592. Min Act: -0.0006

Data Index: 366483 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0573. Min Act: -0.0006

Data Index: 781327 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0573. Min Act: -0.0006

Data Index: 23737 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0572. Min Act: -0.0006

Data Index: 795470 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0573. Min Act: -0.0005

Data Index: 207101 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0611. Min Act: -0.0006

Data Index: 195689 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0560. Min Act: -0.0006

Data Index: 1111984 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0555. Min Act: -0.0006

Data Index: 831260 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0594. Min Act: -0.0006

Data Index: 1144831 (C4 (Web Text))

Max Activating Token Index: 486