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

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

Neuron 3670 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0548. Min Act: -0.0002

Data Index: 199018 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0527. Min Act: -0.0002

Data Index: 922602 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0537. Min Act: -0.0002

Data Index: 130868 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0535. Min Act: -0.0002

Data Index: 670076 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1192367 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0523. Min Act: -0.0002

Data Index: 879410 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0519. Min Act: -0.0002

Data Index: 971049 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0529. Min Act: -0.0002

Data Index: 354911 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1190721 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1299578 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0506. Min Act: -0.0002

Data Index: 263136 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0506. Min Act: -0.0002

Data Index: 469046 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0517. Min Act: -0.0002

Data Index: 627548 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0517. Min Act: -0.0002

Data Index: 962509 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0516. Min Act: -0.0002

Data Index: 831735 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1112711 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1351920 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0512. Min Act: -0.0002

Data Index: 229954 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0510. Min Act: -0.0002

Data Index: 827289 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0509. Min Act: -0.0002

Data Index: 380208 (C4 (Web Text))

Max Activating Token Index: 37