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

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

Neuron 1922 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.5107. Min Act: -0.0000

Data Index: 1080071 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.3299. Min Act: -0.0000

Data Index: 1035647 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.2619. Min Act: -0.0000

Data Index: 659073 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.1675. Min Act: -0.0000

Data Index: 899745 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 1.5107. Min Range: -1.5107

Max Act: 1.0654. Min Act: -0.0000

Data Index: 159631 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 1.5107. Min Range: -1.5107

Max Act: 0.9589. Min Act: -0.0000

Data Index: 513480 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 1.5107. Min Range: -1.5107

Max Act: 0.9990. Min Act: -0.0000

Data Index: 473394 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 1.5107. Min Range: -1.5107

Max Act: 0.9720. Min Act: -0.0000

Data Index: 805131 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 1.5107. Min Range: -1.5107

Max Act: 0.9810. Min Act: -0.0000

Data Index: 708934 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 1.5107. Min Range: -1.5107

Max Act: 0.9546. Min Act: -0.0000

Data Index: 616543 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 1.5107. Min Range: -1.5107

Max Act: 0.9404. Min Act: -0.0000

Data Index: 152953 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 1.5107. Min Range: -1.5107

Max Act: 0.9324. Min Act: -0.0000

Data Index: 556760 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 1.5107. Min Range: -1.5107

Max Act: 0.9167. Min Act: -0.0000

Data Index: 289597 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 1.5107. Min Range: -1.5107

Max Act: 0.9602. Min Act: -0.0000

Data Index: 427295 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 1.5107. Min Range: -1.5107

Max Act: 0.9325. Min Act: -0.0000

Data Index: 448579 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 1.5107. Min Range: -1.5107

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1006830 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 1.5107. Min Range: -1.5107

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1196990 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 1.5107. Min Range: -1.5107

Max Act: 0.8621. Min Act: -0.0000

Data Index: 480761 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 1.5107. Min Range: -1.5107

Max Act: 0.8643. Min Act: -0.0000

Data Index: 902411 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 1.5107. Min Range: -1.5107

Max Act: 0.8602. Min Act: -0.0000

Data Index: 1082017 (C4 (Web Text))

Max Activating Token Index: 899