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

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

Neuron 1370 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: 0.0572. Min Range: -0.0572

Max Act: 0.0572. Min Act: -0.0002

Data Index: 255040 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0534. Min Act: -0.0002

Data Index: 916830 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0524. Min Act: -0.0002

Data Index: 24785 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0449. Min Act: -0.0002

Data Index: 622265 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0439. Min Act: -0.0002

Data Index: 28712 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1316684 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1526010 (Python Code)

Max Activating Token Index: 238

Text #7

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0405. Min Act: -0.0002

Data Index: 384477 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1242164 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0400. Min Act: -0.0002

Data Index: 285854 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1460877 (Python Code)

Max Activating Token Index: 296

Text #11

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0374. Min Act: -0.0002

Data Index: 582082 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0377. Min Act: -0.0002

Data Index: 630485 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0371. Min Act: -0.0002

Data Index: 996683 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0385. Min Act: -0.0002

Data Index: 923159 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0365. Min Act: -0.0002

Data Index: 99508 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1240994 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0359. Min Act: -0.0002

Data Index: 602343 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1375471 (Python Code)

Max Activating Token Index: 493

Text #19

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1392099 (Python Code)

Max Activating Token Index: 258