Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2201 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.4303. Min Act: -0.0002

Data Index: 885740 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3979. Min Act: -0.0001

Data Index: 170987 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.4086. Min Act: -0.0002

Data Index: 420854 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.4018. Min Act: -0.0002

Data Index: 88141 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3974. Min Act: -0.0002

Data Index: 573777 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3833. Min Act: -0.0001

Data Index: 529816 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3923. Min Act: -0.0002

Data Index: 859491 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3889. Min Act: -0.0001

Data Index: 478118 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3779. Min Act: -0.0001

Data Index: 1300286 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3693. Min Act: -0.0001

Data Index: 383621 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3504. Min Act: -0.0001

Data Index: 209039 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3604. Min Act: -0.0001

Data Index: 30625 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3725. Min Act: -0.0002

Data Index: 133337 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3578. Min Act: -0.0002

Data Index: 1069528 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3697. Min Act: -0.0002

Data Index: 930736 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3905. Min Act: -0.0002

Data Index: 82259 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3233. Min Act: -0.0001

Data Index: 310516 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3567. Min Act: -0.0001

Data Index: 506394 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3457. Min Act: -0.0002

Data Index: 1014328 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3346. Min Act: -0.0002

Data Index: 1194347 (C4 (Web Text))

Max Activating Token Index: 522