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

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

Neuron 4896 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0647. Min Act: -0.0002

Data Index: 242400 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0600. Min Act: -0.0002

Data Index: 865979 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0597. Min Act: -0.0002

Data Index: 228386 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0589. Min Act: -0.0002

Data Index: 609938 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0559. Min Act: -0.0002

Data Index: 867156 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1108023 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1320425 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0517. Min Act: -0.0002

Data Index: 104462 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1043196 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0513. Min Act: -0.0002

Data Index: 113622 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1144733 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0494. Min Act: -0.0002

Data Index: 617520 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0496. Min Act: -0.0002

Data Index: 267567 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1148015 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0485. Min Act: -0.0002

Data Index: 324396 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0452. Min Act: -0.0002

Data Index: 246455 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0472. Min Act: -0.0002

Data Index: 314492 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0463. Min Act: -0.0002

Data Index: 485424 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0475. Min Act: -0.0002

Data Index: 511442 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1244917 (C4 (Web Text))

Max Activating Token Index: 187