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

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

Neuron 1192 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: 1.0928. Min Range: -1.0928

Max Act: 1.0928. Min Act: -0.0002

Data Index: 1387655 (Python Code)

Max Activating Token Index: 819

Text #1

Max Range: 1.0928. Min Range: -1.0928

Max Act: 1.0262. Min Act: -0.0002

Data Index: 1420021 (Python Code)

Max Activating Token Index: 849

Text #2

Max Range: 1.0928. Min Range: -1.0928

Max Act: 1.0141. Min Act: -0.0002

Data Index: 1402872 (Python Code)

Max Activating Token Index: 643

Text #3

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.9553. Min Act: -0.0003

Data Index: 422913 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.9523. Min Act: -0.0002

Data Index: 1527887 (Python Code)

Max Activating Token Index: 86

Text #5

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.9193. Min Act: -0.0003

Data Index: 617671 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8859. Min Act: -0.0003

Data Index: 782990 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.9135. Min Act: -0.0002

Data Index: 1506008 (Python Code)

Max Activating Token Index: 845

Text #8

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.9280. Min Act: -0.0003

Data Index: 750319 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8705. Min Act: -0.0003

Data Index: 530898 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8595. Min Act: -0.0003

Data Index: 1267360 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8478. Min Act: -0.0003

Data Index: 611339 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8169. Min Act: -0.0002

Data Index: 1258332 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8495. Min Act: -0.0003

Data Index: 607312 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8277. Min Act: -0.0002

Data Index: 1503648 (Python Code)

Max Activating Token Index: 345

Text #15

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8485. Min Act: -0.0003

Data Index: 397142 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.7952. Min Act: -0.0003

Data Index: 877152 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8288. Min Act: -0.0003

Data Index: 721406 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8029. Min Act: -0.0003

Data Index: 1077553 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.7836. Min Act: -0.0003

Data Index: 357801 (C4 (Web Text))

Max Activating Token Index: 374