Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1638 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0793. Min Act: -0.0002

Data Index: 265222 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0817. Min Act: -0.0002

Data Index: 607090 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0796. Min Act: -0.0002

Data Index: 547053 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1506268 (Python Code)

Max Activating Token Index: 527

Text #4

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1387470 (Python Code)

Max Activating Token Index: 97

Text #5

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0686. Min Act: -0.0002

Data Index: 971189 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0665. Min Act: -0.0002

Data Index: 929307 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1251471 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1254272 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1399045 (Python Code)

Max Activating Token Index: 149

Text #10

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0632. Min Act: -0.0002

Data Index: 237479 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0637. Min Act: -0.0002

Data Index: 616177 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0605. Min Act: -0.0002

Data Index: 868454 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1455085 (Python Code)

Max Activating Token Index: 79

Text #14

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0623. Min Act: -0.0002

Data Index: 911760 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0575. Min Act: -0.0002

Data Index: 581106 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0551. Min Act: -0.0002

Data Index: 870844 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1007369 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1166814 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0519. Min Act: -0.0002

Data Index: 899678 (C4 (Web Text))

Max Activating Token Index: 429