Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3784 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.6708. Min Act: -0.0000

Data Index: 387773 (The Pile)

Max Activating Token Index: 57

Text #1

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.5927. Min Act: -0.0000

Data Index: 261667 (The Pile)

Max Activating Token Index: 427

Text #2

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.3408. Min Act: -0.0000

Data Index: 771079 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1555997 (The Pile)

Max Activating Token Index: 324

Text #4

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.3055. Min Act: -0.0000

Data Index: 316522 (The Pile)

Max Activating Token Index: 273

Text #5

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.3296. Min Act: -0.0000

Data Index: 178055 (The Pile)

Max Activating Token Index: 124

Text #6

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1642709 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.2669. Min Act: -0.0000

Data Index: 506235 (The Pile)

Max Activating Token Index: 928

Text #8

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.2393. Min Act: -0.0000

Data Index: 915198 (The Pile)

Max Activating Token Index: 796

Text #9

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.2916. Min Act: -0.0000

Data Index: 758266 (The Pile)

Max Activating Token Index: 894

Text #10

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.2886. Min Act: -0.0000

Data Index: 310378 (The Pile)

Max Activating Token Index: 491

Text #11

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1344604 (The Pile)

Max Activating Token Index: 91

Text #12

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.2976. Min Act: -0.0000

Data Index: 291657 (The Pile)

Max Activating Token Index: 606

Text #13

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1933959 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.2717. Min Act: -0.0000

Data Index: 1331962 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.2376. Min Act: -0.0000

Data Index: 127582 (The Pile)

Max Activating Token Index: 195

Text #16

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1105387 (The Pile)

Max Activating Token Index: 819

Text #17

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.2617. Min Act: -0.0000

Data Index: 1084635 (The Pile)

Max Activating Token Index: 592

Text #18

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.2609. Min Act: -0.0000

Data Index: 858908 (The Pile)

Max Activating Token Index: 103

Text #19

Max Range: 0.6708. Min Range: -0.6708

Max Act: 0.2695. Min Act: -0.0000

Data Index: 446445 (The Pile)

Max Activating Token Index: 153