Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3093 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3464. Min Act: -0.0001

Data Index: 1459954 (Python Code)

Max Activating Token Index: 133

Text #1

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3560. Min Act: -0.0001

Data Index: 1656241 (Python Code)

Max Activating Token Index: 165

Text #2

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3288. Min Act: -0.0001

Data Index: 1506880 (Python Code)

Max Activating Token Index: 873

Text #3

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1430722 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2916. Min Act: -0.0000

Data Index: 856514 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1471146 (Python Code)

Max Activating Token Index: 192

Text #6

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1387278 (Python Code)

Max Activating Token Index: 515

Text #7

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2483. Min Act: -0.0000

Data Index: 753182 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2666. Min Act: -0.0001

Data Index: 185886 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2580. Min Act: -0.0001

Data Index: 281650 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2565. Min Act: -0.0001

Data Index: 358564 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2727. Min Act: -0.0001

Data Index: 1372580 (Python Code)

Max Activating Token Index: 143

Text #12

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2617. Min Act: -0.0001

Data Index: 699 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1498139 (Python Code)

Max Activating Token Index: 306

Text #14

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2723. Min Act: -0.0000

Data Index: 1350410 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2583. Min Act: -0.0001

Data Index: 1538682 (Python Code)

Max Activating Token Index: 34

Text #16

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1633206 (Python Code)

Max Activating Token Index: 549

Text #17

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2914. Min Act: -0.0001

Data Index: 943436 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2568. Min Act: -0.0001

Data Index: 1263087 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1655414 (Python Code)

Max Activating Token Index: 671