Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4003 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0869. Min Act: -0.0000

Data Index: 598975 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0593. Min Act: -0.0000

Data Index: 901322 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0605. Min Act: -0.0000

Data Index: 1006840 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0581. Min Act: -0.0000

Data Index: 286144 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0599. Min Act: -0.0000

Data Index: 193534 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0601. Min Act: -0.0000

Data Index: 1647449 (Python Code)

Max Activating Token Index: 358

Text #6

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0522. Min Act: -0.0000

Data Index: 420897 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0601. Min Act: -0.0000

Data Index: 1522374 (Python Code)

Max Activating Token Index: 77

Text #8

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1033859 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0567. Min Act: -0.0000

Data Index: 354020 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0543. Min Act: -0.0000

Data Index: 1030756 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0506. Min Act: -0.0000

Data Index: 1589296 (Python Code)

Max Activating Token Index: 166

Text #12

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0521. Min Act: -0.0000

Data Index: 861423 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0478. Min Act: -0.0000

Data Index: 33631 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0508. Min Act: -0.0000

Data Index: 1449755 (Python Code)

Max Activating Token Index: 30

Text #15

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0517. Min Act: -0.0000

Data Index: 1121593 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0460. Min Act: -0.0000

Data Index: 1463724 (Python Code)

Max Activating Token Index: 234

Text #17

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0421. Min Act: -0.0000

Data Index: 1177133 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0477. Min Act: -0.0000

Data Index: 457781 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0475. Min Act: -0.0000

Data Index: 17820 (C4 (Web Text))

Max Activating Token Index: 588