Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 805 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2844. Min Act: -0.0002

Data Index: 1561663 (Python Code)

Max Activating Token Index: 914

Text #1

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2872. Min Act: -0.0002

Data Index: 1602225 (Python Code)

Max Activating Token Index: 839

Text #2

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2544. Min Act: -0.0002

Data Index: 1567971 (Python Code)

Max Activating Token Index: 1016

Text #3

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2573. Min Act: -0.0002

Data Index: 1479712 (Python Code)

Max Activating Token Index: 530

Text #4

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2763. Min Act: -0.0002

Data Index: 1598018 (Python Code)

Max Activating Token Index: 12

Text #5

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2420. Min Act: -0.0002

Data Index: 1629868 (Python Code)

Max Activating Token Index: 767

Text #6

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2496. Min Act: -0.0002

Data Index: 1499465 (Python Code)

Max Activating Token Index: 101

Text #7

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2594. Min Act: -0.0002

Data Index: 1533543 (Python Code)

Max Activating Token Index: 993

Text #8

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2548. Min Act: -0.0003

Data Index: 1457198 (Python Code)

Max Activating Token Index: 1010

Text #9

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2546. Min Act: -0.0002

Data Index: 1551415 (Python Code)

Max Activating Token Index: 555

Text #10

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2512. Min Act: -0.0002

Data Index: 1511287 (Python Code)

Max Activating Token Index: 284

Text #11

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2503. Min Act: -0.0002

Data Index: 1644460 (Python Code)

Max Activating Token Index: 560

Text #12

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2350. Min Act: -0.0002

Data Index: 1454771 (Python Code)

Max Activating Token Index: 615

Text #13

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2457. Min Act: -0.0002

Data Index: 1475893 (Python Code)

Max Activating Token Index: 247

Text #14

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2082. Min Act: -0.0002

Data Index: 1426788 (Python Code)

Max Activating Token Index: 332

Text #15

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2434. Min Act: -0.0002

Data Index: 1386354 (Python Code)

Max Activating Token Index: 201

Text #16

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2332. Min Act: -0.0002

Data Index: 1595976 (Python Code)

Max Activating Token Index: 169

Text #17

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2486. Min Act: -0.0002

Data Index: 1642435 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2431. Min Act: -0.0002

Data Index: 1371601 (Python Code)

Max Activating Token Index: 933

Text #19

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2326. Min Act: -0.0002

Data Index: 1613531 (Python Code)

Max Activating Token Index: 17