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

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

Neuron 704 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.3473. Min Act: 0.0001

Data Index: 519894 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.0817. Min Act: -0.0000

Data Index: 1533650 (Python Code)

Max Activating Token Index: 340

Text #2

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.1435. Min Act: -0.0001

Data Index: 1445898 (Python Code)

Max Activating Token Index: 452

Text #3

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.0117. Min Act: -0.0000

Data Index: 1459112 (Python Code)

Max Activating Token Index: 285

Text #4

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.9620. Min Act: -0.0000

Data Index: 406869 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1572865 (Python Code)

Max Activating Token Index: 872

Text #6

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8766. Min Act: -0.0000

Data Index: 909198 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8616. Min Act: -0.0000

Data Index: 1414401 (Python Code)

Max Activating Token Index: 869

Text #8

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8242. Min Act: 0.0000

Data Index: 1262918 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8717. Min Act: -0.0000

Data Index: 214793 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8469. Min Act: -0.0000

Data Index: 603233 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8078. Min Act: -0.0000

Data Index: 539995 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8803. Min Act: 0.0000

Data Index: 705006 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8027. Min Act: -0.0000

Data Index: 1210979 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1269801 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.7789. Min Act: -0.0000

Data Index: 75921 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.7639. Min Act: 0.0000

Data Index: 1069050 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.7332. Min Act: -0.0000

Data Index: 708996 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.7542. Min Act: -0.0000

Data Index: 909620 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.7410. Min Act: -0.0000

Data Index: 928837 (C4 (Web Text))

Max Activating Token Index: 226