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

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

Neuron 3292 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0959. Min Act: -0.0001

Data Index: 811706 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1089902 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0808. Min Act: -0.0000

Data Index: 1584864 (Python Code)

Max Activating Token Index: 576

Text #3

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0727. Min Act: -0.0001

Data Index: 1334426 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1243751 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1091973 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0725. Min Act: -0.0000

Data Index: 1587308 (Python Code)

Max Activating Token Index: 667

Text #7

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0653. Min Act: -0.0001

Data Index: 216883 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0709. Min Act: -0.0001

Data Index: 102519 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0681. Min Act: -0.0000

Data Index: 1635350 (Python Code)

Max Activating Token Index: 220

Text #10

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1063183 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0647. Min Act: -0.0001

Data Index: 653594 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1413640 (Python Code)

Max Activating Token Index: 744

Text #13

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0619. Min Act: -0.0000

Data Index: 1497127 (Python Code)

Max Activating Token Index: 956

Text #14

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1518541 (Python Code)

Max Activating Token Index: 591

Text #15

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0584. Min Act: -0.0001

Data Index: 537062 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1606235 (Python Code)

Max Activating Token Index: 46

Text #17

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0631. Min Act: -0.0000

Data Index: 1384093 (Python Code)

Max Activating Token Index: 110

Text #18

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0514. Min Act: -0.0001

Data Index: 766917 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0560. Min Act: -0.0000

Data Index: 1464443 (Python Code)

Max Activating Token Index: 585