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

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

Neuron 4560 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3725. Min Range: -2.3725

Max Act: 2.3725. Min Act: -0.0000

Data Index: 399040 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 2.3725. Min Range: -2.3725

Max Act: 2.1132. Min Act: -0.0000

Data Index: 1260803 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.9672. Min Act: -0.0000

Data Index: 358477 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.9553. Min Act: -0.0000

Data Index: 253332 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.9040. Min Act: -0.0000

Data Index: 25863 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.8669. Min Act: -0.0000

Data Index: 942225 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.8633. Min Act: -0.0000

Data Index: 1324073 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.8499. Min Act: -0.0000

Data Index: 452512 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.8364. Min Act: -0.0000

Data Index: 1295300 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.7991. Min Act: -0.0000

Data Index: 1198184 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.7941. Min Act: -0.0000

Data Index: 379506 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.7938. Min Act: -0.0000

Data Index: 471246 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.8872. Min Act: -0.0000

Data Index: 989266 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.7715. Min Act: -0.0000

Data Index: 1079904 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.7734. Min Act: -0.0000

Data Index: 889660 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.6594. Min Act: -0.0000

Data Index: 740886 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.6535. Min Act: -0.0000

Data Index: 63858 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.7422. Min Act: -0.0000

Data Index: 1076008 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.7375. Min Act: -0.0000

Data Index: 961379 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 2.3725. Min Range: -2.3725

Max Act: 1.7064. Min Act: -0.0000

Data Index: 1186025 (C4 (Web Text))

Max Activating Token Index: 483