Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1853 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2684. Min Act: -0.0006

Data Index: 123891 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2627. Min Act: -0.0006

Data Index: 829060 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2593. Min Act: -0.0006

Data Index: 443931 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2576. Min Act: -0.0006

Data Index: 760870 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2619. Min Act: -0.0006

Data Index: 1014164 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2531. Min Act: -0.0006

Data Index: 512601 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2535. Min Act: -0.0006

Data Index: 918886 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2535. Min Act: -0.0006

Data Index: 1271449 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2578. Min Act: -0.0006

Data Index: 1031085 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2532. Min Act: -0.0006

Data Index: 363513 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2531. Min Act: -0.0006

Data Index: 11975 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2531. Min Act: -0.0006

Data Index: 1188771 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2531. Min Act: -0.0006

Data Index: 193716 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2574. Min Act: -0.0006

Data Index: 859609 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2529. Min Act: -0.0005

Data Index: 512278 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2569. Min Act: -0.0006

Data Index: 751455 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2518. Min Act: -0.0006

Data Index: 1131915 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2521. Min Act: -0.0006

Data Index: 869149 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2520. Min Act: -0.0006

Data Index: 225446 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2520. Min Act: -0.0006

Data Index: 306457 (C4 (Web Text))

Max Activating Token Index: 80