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

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

Neuron 2589 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0679. Min Act: -0.0001

Data Index: 94255 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0647. Min Act: -0.0001

Data Index: 326553 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1476402 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0538. Min Act: -0.0001

Data Index: 561909 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0580. Min Act: -0.0001

Data Index: 424149 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0546. Min Act: -0.0001

Data Index: 411543 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0508. Min Act: -0.0001

Data Index: 160171 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0541. Min Act: -0.0001

Data Index: 706866 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1286031 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0542. Min Act: -0.0001

Data Index: 1460240 (Python Code)

Max Activating Token Index: 627

Text #10

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0501. Min Act: -0.0002

Data Index: 220036 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1325197 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0514. Min Act: -0.0001

Data Index: 66309 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1616817 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1254723 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0598. Min Act: -0.0001

Data Index: 976569 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0531. Min Act: -0.0001

Data Index: 824507 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0549. Min Act: -0.0002

Data Index: 144392 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0532. Min Act: -0.0001

Data Index: 1387479 (Python Code)

Max Activating Token Index: 864

Text #19

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0508. Min Act: -0.0001

Data Index: 716735 (C4 (Web Text))

Max Activating Token Index: 94