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

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

Neuron 2381 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1423024 (Python Code)

Max Activating Token Index: 887

Text #1

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.6292. Min Act: -0.0000

Data Index: 1583262 (Python Code)

Max Activating Token Index: 641

Text #2

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1634136 (Python Code)

Max Activating Token Index: 687

Text #3

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4296. Min Act: -0.0000

Data Index: 686062 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3810. Min Act: -0.0000

Data Index: 106798 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3972. Min Act: -0.0000

Data Index: 81414 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1587657 (Python Code)

Max Activating Token Index: 459

Text #7

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1428105 (Python Code)

Max Activating Token Index: 665

Text #8

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1641896 (Python Code)

Max Activating Token Index: 802

Text #9

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3735. Min Act: -0.0000

Data Index: 1556123 (Python Code)

Max Activating Token Index: 477

Text #10

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1527548 (Python Code)

Max Activating Token Index: 635

Text #11

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1585473 (Python Code)

Max Activating Token Index: 276

Text #12

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3451. Min Act: -0.0000

Data Index: 1400823 (Python Code)

Max Activating Token Index: 535

Text #13

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1426137 (Python Code)

Max Activating Token Index: 666

Text #14

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1363969 (Python Code)

Max Activating Token Index: 123

Text #15

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1395792 (Python Code)

Max Activating Token Index: 594

Text #16

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3386. Min Act: -0.0000

Data Index: 1501219 (Python Code)

Max Activating Token Index: 144

Text #17

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1527377 (Python Code)

Max Activating Token Index: 404

Text #18

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3472. Min Act: -0.0000

Data Index: 1371590 (Python Code)

Max Activating Token Index: 767

Text #19

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1509169 (Python Code)

Max Activating Token Index: 156