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

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

Neuron 3 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: 0.2911. Min Range: -0.2911

Max Act: 0.2707. Min Act: -0.0002

Data Index: 1482491 (Python Code)

Max Activating Token Index: 644

Text #1

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2911. Min Act: -0.0002

Data Index: 1367609 (Python Code)

Max Activating Token Index: 519

Text #2

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2802. Min Act: -0.0002

Data Index: 1588514 (Python Code)

Max Activating Token Index: 859

Text #3

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2519. Min Act: -0.0002

Data Index: 1426451 (Python Code)

Max Activating Token Index: 449

Text #4

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2691. Min Act: -0.0002

Data Index: 1447963 (Python Code)

Max Activating Token Index: 525

Text #5

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2476. Min Act: -0.0002

Data Index: 1364626 (Python Code)

Max Activating Token Index: 141

Text #6

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2479. Min Act: -0.0002

Data Index: 1480008 (Python Code)

Max Activating Token Index: 339

Text #7

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2455. Min Act: -0.0002

Data Index: 1583223 (Python Code)

Max Activating Token Index: 877

Text #8

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2670. Min Act: -0.0002

Data Index: 1531436 (Python Code)

Max Activating Token Index: 858

Text #9

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2493. Min Act: -0.0002

Data Index: 1577834 (Python Code)

Max Activating Token Index: 514

Text #10

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2412. Min Act: -0.0002

Data Index: 1600289 (Python Code)

Max Activating Token Index: 535

Text #11

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2446. Min Act: -0.0002

Data Index: 1371905 (Python Code)

Max Activating Token Index: 778

Text #12

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2350. Min Act: -0.0002

Data Index: 1410703 (Python Code)

Max Activating Token Index: 962

Text #13

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2377. Min Act: -0.0002

Data Index: 1479181 (Python Code)

Max Activating Token Index: 702

Text #14

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2358. Min Act: -0.0002

Data Index: 1597652 (Python Code)

Max Activating Token Index: 380

Text #15

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2292. Min Act: -0.0002

Data Index: 1598083 (Python Code)

Max Activating Token Index: 616

Text #16

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2363. Min Act: -0.0002

Data Index: 1493375 (Python Code)

Max Activating Token Index: 402

Text #17

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2413. Min Act: -0.0002

Data Index: 1388093 (Python Code)

Max Activating Token Index: 568

Text #18

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2259. Min Act: -0.0002

Data Index: 1375842 (Python Code)

Max Activating Token Index: 191

Text #19

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2348. Min Act: -0.0002

Data Index: 1630291 (Python Code)

Max Activating Token Index: 1012