Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1106 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1416601 (Python Code)

Max Activating Token Index: 977

Text #1

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1629089 (Python Code)

Max Activating Token Index: 471

Text #2

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1399609 (Python Code)

Max Activating Token Index: 498

Text #3

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1489512 (Python Code)

Max Activating Token Index: 563

Text #4

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1437248 (Python Code)

Max Activating Token Index: 557

Text #5

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1382576 (Python Code)

Max Activating Token Index: 649

Text #6

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1518771 (Python Code)

Max Activating Token Index: 711

Text #7

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0373. Min Act: -0.0002

Data Index: 1542472 (Python Code)

Max Activating Token Index: 786

Text #8

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1566893 (Python Code)

Max Activating Token Index: 128

Text #9

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1414297 (Python Code)

Max Activating Token Index: 402

Text #10

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1401588 (Python Code)

Max Activating Token Index: 280

Text #11

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1438564 (Python Code)

Max Activating Token Index: 1005

Text #12

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1520538 (Python Code)

Max Activating Token Index: 273

Text #13

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0358. Min Act: -0.0003

Data Index: 272311 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1363759 (Python Code)

Max Activating Token Index: 863

Text #15

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1604366 (Python Code)

Max Activating Token Index: 445

Text #16

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1404103 (Python Code)

Max Activating Token Index: 511

Text #17

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1415034 (Python Code)

Max Activating Token Index: 152

Text #18

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1569210 (Python Code)

Max Activating Token Index: 808

Text #19

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0326. Min Act: -0.0002

Data Index: 99113 (C4 (Web Text))

Max Activating Token Index: 639