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

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

Neuron 1100 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: 0.8298. Min Range: -0.8298

Max Act: 0.8298. Min Act: -0.0000

Data Index: 521350 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.7346. Min Act: -0.0000

Data Index: 742721 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6714. Min Act: -0.0000

Data Index: 153675 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1010900 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1262083 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1281868 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5387. Min Act: -0.0000

Data Index: 570043 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5596. Min Act: -0.0000

Data Index: 308187 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5712. Min Act: -0.0000

Data Index: 1218923 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.6059. Min Act: -0.0000

Data Index: 476010 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5002. Min Act: -0.0000

Data Index: 958133 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1198282 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5381. Min Act: -0.0000

Data Index: 611990 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5877. Min Act: 0.0000

Data Index: 1352564 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.4805. Min Act: -0.0000

Data Index: 594544 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5564. Min Act: -0.0000

Data Index: 336925 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.4915. Min Act: -0.0000

Data Index: 776959 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1301186 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.4838. Min Act: -0.0000

Data Index: 1233602 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.8298. Min Range: -0.8298

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1126063 (C4 (Web Text))

Max Activating Token Index: 357