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

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

Neuron 3395 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3594. Min Act: -0.0000

Data Index: 1331624 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3483. Min Act: -0.0000

Data Index: 300181 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3659. Min Act: -0.0000

Data Index: 378438 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3433. Min Act: -0.0000

Data Index: 356059 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3463. Min Act: -0.0000

Data Index: 640300 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1234150 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3378. Min Act: -0.0000

Data Index: 900475 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3242. Min Act: -0.0000

Data Index: 117883 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3265. Min Act: -0.0000

Data Index: 381123 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3243. Min Act: -0.0000

Data Index: 732342 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2908. Min Act: -0.0000

Data Index: 775529 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3086. Min Act: -0.0000

Data Index: 983724 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3496. Min Act: -0.0000

Data Index: 230533 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3021. Min Act: -0.0000

Data Index: 599271 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1285765 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1049314 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2913. Min Act: -0.0000

Data Index: 563640 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3086. Min Act: -0.0000

Data Index: 599545 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2962. Min Act: -0.0000

Data Index: 323790 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2746. Min Act: -0.0000

Data Index: 1189525 (C4 (Web Text))

Max Activating Token Index: 548