Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2491 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0411. Min Act: -0.0004

Data Index: 1439117 (Python Code)

Max Activating Token Index: 813

Text #1

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0364. Min Act: -0.0004

Data Index: 1483723 (Python Code)

Max Activating Token Index: 262

Text #2

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0355. Min Act: -0.0004

Data Index: 1401738 (Python Code)

Max Activating Token Index: 334

Text #3

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0369. Min Act: -0.0004

Data Index: 1560293 (Python Code)

Max Activating Token Index: 493

Text #4

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0402. Min Act: -0.0004

Data Index: 1360756 (Python Code)

Max Activating Token Index: 217

Text #5

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0334. Min Act: -0.0004

Data Index: 1420674 (Python Code)

Max Activating Token Index: 406

Text #6

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0342. Min Act: -0.0004

Data Index: 1593347 (Python Code)

Max Activating Token Index: 168

Text #7

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0346. Min Act: -0.0004

Data Index: 1618429 (Python Code)

Max Activating Token Index: 445

Text #8

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0240. Min Act: -0.0004

Data Index: 1387523 (Python Code)

Max Activating Token Index: 872

Text #9

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0288. Min Act: -0.0004

Data Index: 1495296 (Python Code)

Max Activating Token Index: 584

Text #10

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0318. Min Act: -0.0004

Data Index: 1631421 (Python Code)

Max Activating Token Index: 292

Text #11

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0363. Min Act: -0.0004

Data Index: 1507491 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0331. Min Act: -0.0004

Data Index: 1426861 (Python Code)

Max Activating Token Index: 874

Text #13

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0286. Min Act: -0.0004

Data Index: 1605433 (Python Code)

Max Activating Token Index: 410

Text #14

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0318. Min Act: -0.0004

Data Index: 1641196 (Python Code)

Max Activating Token Index: 59

Text #15

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0311. Min Act: -0.0004

Data Index: 1550542 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0293. Min Act: -0.0004

Data Index: 1459863 (Python Code)

Max Activating Token Index: 677

Text #17

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0335. Min Act: -0.0004

Data Index: 1575784 (Python Code)

Max Activating Token Index: 397

Text #18

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0308. Min Act: -0.0004

Data Index: 1505802 (Python Code)

Max Activating Token Index: 100

Text #19

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0253. Min Act: -0.0004

Data Index: 1379056 (Python Code)

Max Activating Token Index: 551