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

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

Neuron 4838 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0650. Min Act: -0.0003

Data Index: 824578 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0684. Min Act: -0.0003

Data Index: 90994 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0611. Min Act: -0.0003

Data Index: 931948 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0622. Min Act: -0.0002

Data Index: 114393 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0620. Min Act: -0.0003

Data Index: 941973 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0588. Min Act: -0.0003

Data Index: 583624 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0548. Min Act: -0.0002

Data Index: 748150 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1002947 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0552. Min Act: -0.0002

Data Index: 245143 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0514. Min Act: -0.0003

Data Index: 845204 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0487. Min Act: -0.0003

Data Index: 908108 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0500. Min Act: -0.0003

Data Index: 128279 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0466. Min Act: -0.0003

Data Index: 466297 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0488. Min Act: -0.0002

Data Index: 18164 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1248103 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0488. Min Act: -0.0003

Data Index: 347288 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0464. Min Act: -0.0002

Data Index: 959158 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1267299 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0451. Min Act: -0.0003

Data Index: 825686 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0430. Min Act: -0.0002

Data Index: 141936 (C4 (Web Text))

Max Activating Token Index: 604