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

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

Neuron 1538 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4966. Min Act: -0.0000

Data Index: 858491 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4677. Min Act: -0.0000

Data Index: 663378 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4416. Min Act: -0.0000

Data Index: 124450 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4216. Min Act: -0.0000

Data Index: 791180 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3947. Min Act: -0.0000

Data Index: 143864 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3752. Min Act: -0.0000

Data Index: 530345 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1288507 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3841. Min Act: -0.0000

Data Index: 106735 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3646. Min Act: 0.0000

Data Index: 1652467 (Python Code)

Max Activating Token Index: 165

Text #9

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3634. Min Act: -0.0000

Data Index: 306855 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3395. Min Act: -0.0000

Data Index: 705672 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1116152 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3512. Min Act: -0.0000

Data Index: 984420 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3352. Min Act: -0.0000

Data Index: 56358 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3576. Min Act: -0.0000

Data Index: 110545 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3597. Min Act: -0.0000

Data Index: 851773 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1197389 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1099674 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3368. Min Act: -0.0000

Data Index: 995816 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3466. Min Act: -0.0000

Data Index: 1150546 (C4 (Web Text))

Max Activating Token Index: 291