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

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

Neuron 3703 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.5918. Min Act: -0.0000

Data Index: 1490710 (Python Code)

Max Activating Token Index: 587

Text #1

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.6723. Min Act: -0.0000

Data Index: 1569657 (Python Code)

Max Activating Token Index: 648

Text #2

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.5316. Min Act: -0.0000

Data Index: 1653580 (Python Code)

Max Activating Token Index: 552

Text #3

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.5662. Min Act: -0.0000

Data Index: 1533437 (Python Code)

Max Activating Token Index: 805

Text #4

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.5796. Min Act: -0.0000

Data Index: 1518453 (Python Code)

Max Activating Token Index: 822

Text #5

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.4356. Min Act: -0.0000

Data Index: 1502395 (Python Code)

Max Activating Token Index: 392

Text #6

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.4494. Min Act: -0.0000

Data Index: 1104275 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.3026. Min Act: -0.0000

Data Index: 1534975 (Python Code)

Max Activating Token Index: 660

Text #8

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.3532. Min Act: -0.0000

Data Index: 1409481 (Python Code)

Max Activating Token Index: 188

Text #9

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.2438. Min Act: -0.0000

Data Index: 1314815 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.3073. Min Act: -0.0000

Data Index: 1371789 (Python Code)

Max Activating Token Index: 268

Text #11

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.3027. Min Act: -0.0000

Data Index: 469633 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.2383. Min Act: -0.0000

Data Index: 1386370 (Python Code)

Max Activating Token Index: 590

Text #13

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.1775. Min Act: -0.0000

Data Index: 1578873 (Python Code)

Max Activating Token Index: 556

Text #14

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.1343. Min Act: -0.0000

Data Index: 1522741 (Python Code)

Max Activating Token Index: 482

Text #15

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.1519. Min Act: -0.0000

Data Index: 29912 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.1349. Min Act: -0.0000

Data Index: 1498531 (Python Code)

Max Activating Token Index: 176

Text #17

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.1026. Min Act: -0.0000

Data Index: 1433017 (Python Code)

Max Activating Token Index: 479

Text #18

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.0572. Min Act: -0.0000

Data Index: 1647584 (Python Code)

Max Activating Token Index: 169

Text #19

Max Range: 1.6723. Min Range: -1.6723

Max Act: 1.2393. Min Act: -0.0000

Data Index: 112483 (C4 (Web Text))

Max Activating Token Index: 773