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

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

Neuron 3080 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: 1.4849. Min Range: -1.4849

Max Act: 1.4849. Min Act: -0.0002

Data Index: 767434 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.3740. Min Act: -0.0002

Data Index: 1417786 (Python Code)

Max Activating Token Index: 284

Text #2

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.4256. Min Act: -0.0002

Data Index: 116646 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.4256. Min Act: -0.0002

Data Index: 1404932 (Python Code)

Max Activating Token Index: 2

Text #4

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.4256. Min Act: -0.0002

Data Index: 353369 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.4256. Min Act: -0.0002

Data Index: 89721 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.1895. Min Act: -0.0002

Data Index: 863483 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.3333. Min Act: -0.0002

Data Index: 1435169 (Python Code)

Max Activating Token Index: 320

Text #8

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.3983. Min Act: -0.0002

Data Index: 952310 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.2781. Min Act: -0.0002

Data Index: 1358445 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.2901. Min Act: -0.0002

Data Index: 1587228 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.2287. Min Act: -0.0002

Data Index: 1412867 (Python Code)

Max Activating Token Index: 206

Text #12

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.3280. Min Act: -0.0002

Data Index: 1436246 (Python Code)

Max Activating Token Index: 439

Text #13

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.4574. Min Act: -0.0002

Data Index: 690903 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.3168. Min Act: -0.0002

Data Index: 1435069 (Python Code)

Max Activating Token Index: 812

Text #15

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.2473. Min Act: -0.0002

Data Index: 839431 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.2153. Min Act: -0.0002

Data Index: 816912 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.2848. Min Act: -0.0002

Data Index: 1646091 (Python Code)

Max Activating Token Index: 595

Text #18

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.2401. Min Act: -0.0002

Data Index: 1589269 (Python Code)

Max Activating Token Index: 598

Text #19

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.2765. Min Act: -0.0002

Data Index: 1335807 (C4 (Web Text))

Max Activating Token Index: 68