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

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

Neuron 3919 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: 0.0631. Min Range: -0.0631

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1324236 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0522. Min Act: -0.0002

Data Index: 154997 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1122490 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0510. Min Act: -0.0002

Data Index: 382104 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0483. Min Act: -0.0002

Data Index: 705919 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0482. Min Act: -0.0002

Data Index: 733270 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1016791 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0459. Min Act: -0.0002

Data Index: 925586 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1120397 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0471. Min Act: -0.0002

Data Index: 490917 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0464. Min Act: -0.0002

Data Index: 120365 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0445. Min Act: -0.0002

Data Index: 371660 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0458. Min Act: -0.0002

Data Index: 433611 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1170880 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0450. Min Act: -0.0002

Data Index: 741490 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0433. Min Act: -0.0002

Data Index: 398348 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0479. Min Act: -0.0002

Data Index: 844122 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0441. Min Act: -0.0002

Data Index: 715853 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0424. Min Act: -0.0002

Data Index: 290657 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0456. Min Act: -0.0002

Data Index: 955383 (C4 (Web Text))

Max Activating Token Index: 825