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

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

Neuron 3508 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: 1.3665. Min Range: -1.3665

Max Act: 1.3061. Min Act: -0.0000

Data Index: 1167791 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.3665. Min Act: -0.0000

Data Index: 771458 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.1969. Min Act: -0.0000

Data Index: 656659 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.1967. Min Act: -0.0000

Data Index: 422589 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.2097. Min Act: -0.0000

Data Index: 1483455 (Python Code)

Max Activating Token Index: 887

Text #5

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.0961. Min Act: -0.0000

Data Index: 19678 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1541090 (Python Code)

Max Activating Token Index: 56

Text #7

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.1563. Min Act: -0.0000

Data Index: 1018426 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.1450. Min Act: -0.0000

Data Index: 1436441 (Python Code)

Max Activating Token Index: 546

Text #9

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.1551. Min Act: -0.0000

Data Index: 56169 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.0492. Min Act: -0.0000

Data Index: 539348 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.1246. Min Act: -0.0000

Data Index: 262331 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.1257. Min Act: -0.0000

Data Index: 1008396 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.1069. Min Act: -0.0000

Data Index: 694509 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.3461. Min Act: -0.0000

Data Index: 310066 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.0178. Min Act: -0.0000

Data Index: 1090984 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.0098. Min Act: -0.0000

Data Index: 808338 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 1.3665. Min Range: -1.3665

Max Act: 0.9979. Min Act: -0.0000

Data Index: 128131 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.0364. Min Act: -0.0000

Data Index: 1479612 (Python Code)

Max Activating Token Index: 78

Text #19

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.0551. Min Act: -0.0000

Data Index: 1411366 (Python Code)

Max Activating Token Index: 766