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

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

Neuron 971 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0674. Min Act: -0.0002

Data Index: 760465 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0546. Min Act: -0.0003

Data Index: 990178 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1580517 (Python Code)

Max Activating Token Index: 75

Text #3

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0534. Min Act: -0.0002

Data Index: 125273 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0467. Min Act: -0.0002

Data Index: 566965 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1373581 (Python Code)

Max Activating Token Index: 144

Text #6

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1494671 (Python Code)

Max Activating Token Index: 67

Text #7

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0533. Min Act: -0.0002

Data Index: 935164 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0476. Min Act: -0.0002

Data Index: 584415 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0447. Min Act: -0.0002

Data Index: 209758 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1453983 (Python Code)

Max Activating Token Index: 85

Text #11

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1547352 (Python Code)

Max Activating Token Index: 710

Text #12

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1385808 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1266709 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1463341 (Python Code)

Max Activating Token Index: 255

Text #15

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1134673 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0480. Min Act: -0.0002

Data Index: 683654 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1635670 (Python Code)

Max Activating Token Index: 897

Text #18

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1084082 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1004114 (C4 (Web Text))

Max Activating Token Index: 23