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

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

Neuron 2642 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.1636. Min Act: -0.0002

Data Index: 528783 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.1028. Min Act: -0.0002

Data Index: 349278 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.0409. Min Act: -0.0002

Data Index: 1246121 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9415. Min Act: -0.0002

Data Index: 48474 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9858. Min Act: -0.0002

Data Index: 7591 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8985. Min Act: -0.0002

Data Index: 380611 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9646. Min Act: -0.0002

Data Index: 1265718 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9879. Min Act: -0.0002

Data Index: 168218 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8566. Min Act: -0.0002

Data Index: 734059 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8920. Min Act: -0.0002

Data Index: 367081 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9086. Min Act: -0.0002

Data Index: 515993 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9183. Min Act: -0.0002

Data Index: 1024230 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8262. Min Act: -0.0002

Data Index: 350480 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8380. Min Act: -0.0002

Data Index: 1027784 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8185. Min Act: -0.0002

Data Index: 1045308 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8638. Min Act: -0.0002

Data Index: 491423 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8364. Min Act: -0.0002

Data Index: 1044335 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8758. Min Act: -0.0002

Data Index: 513302 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8558. Min Act: -0.0002

Data Index: 357321 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8585. Min Act: -0.0002

Data Index: 941467 (C4 (Web Text))

Max Activating Token Index: 463