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

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

Neuron 4034 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: 0.0567. Min Range: -0.0567

Max Act: 0.0567. Min Act: -0.0003

Data Index: 735732 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0546. Min Act: -0.0003

Data Index: 684803 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0504. Min Act: -0.0003

Data Index: 209323 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0515. Min Act: -0.0003

Data Index: 420289 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0466. Min Act: -0.0003

Data Index: 111455 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0483. Min Act: -0.0003

Data Index: 190099 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0461. Min Act: -0.0003

Data Index: 1222905 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0453. Min Act: -0.0003

Data Index: 964831 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0470. Min Act: -0.0003

Data Index: 480719 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1248922 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0447. Min Act: -0.0003

Data Index: 365516 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1314870 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0424. Min Act: -0.0003

Data Index: 629276 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0457. Min Act: -0.0003

Data Index: 363190 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0453. Min Act: -0.0003

Data Index: 291925 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0418. Min Act: -0.0003

Data Index: 1200913 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1247129 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1170184 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0412. Min Act: -0.0003

Data Index: 1185026 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0421. Min Act: -0.0003

Data Index: 879800 (C4 (Web Text))

Max Activating Token Index: 369