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

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

Neuron 2668 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.0000

Data Index: 571930 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7060. Min Act: -0.0000

Data Index: 643297 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.4484. Min Act: -0.0000

Data Index: 148094 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.9231. Min Act: -0.0000

Data Index: 1096700 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.8868. Min Act: -0.0000

Data Index: 527613 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.6609. Min Act: -0.0000

Data Index: 148156 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.7878. Min Act: -0.0000

Data Index: 1109561 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.7688. Min Act: -0.0000

Data Index: 1270952 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.8811. Min Act: -0.0000

Data Index: 475005 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.5963. Min Act: -0.0000

Data Index: 39703 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.7270. Min Act: -0.0000

Data Index: 15703 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.6901. Min Act: -0.0000

Data Index: 1117749 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.8217. Min Act: -0.0000

Data Index: 704300 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.6462. Min Act: -0.0000

Data Index: 530465 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.3585. Min Act: -0.0000

Data Index: 981619 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.4574. Min Act: -0.0000

Data Index: 940771 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.4724. Min Act: -0.0000

Data Index: 950941 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.5623. Min Act: -0.0000

Data Index: 1014054 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.4433. Min Act: -0.0000

Data Index: 187772 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 3.7107. Min Range: -3.7107

Max Act: 2.2890. Min Act: -0.0000

Data Index: 196140 (C4 (Web Text))

Max Activating Token Index: 858