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

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

Neuron 3332 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: 0.9664. Min Range: -0.9664

Max Act: 0.9577. Min Act: -0.0000

Data Index: 894919 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.9664. Min Act: -0.0000

Data Index: 575177 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.9623. Min Act: -0.0000

Data Index: 819366 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.9463. Min Act: -0.0000

Data Index: 619500 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1097113 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.9286. Min Act: -0.0000

Data Index: 1145159 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.9167. Min Act: -0.0000

Data Index: 1048812 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.9126. Min Act: -0.0000

Data Index: 489143 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.9331. Min Act: -0.0000

Data Index: 272316 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.9063. Min Act: -0.0000

Data Index: 107797 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.9195. Min Act: -0.0000

Data Index: 1030959 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.8815. Min Act: -0.0000

Data Index: 40314 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.9021. Min Act: -0.0000

Data Index: 361948 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.8783. Min Act: -0.0000

Data Index: 367606 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.8414. Min Act: -0.0000

Data Index: 229432 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.8628. Min Act: -0.0000

Data Index: 422698 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.8631. Min Act: -0.0000

Data Index: 988729 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1123191 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.8585. Min Act: -0.0000

Data Index: 1054008 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.9664. Min Range: -0.9664

Max Act: 0.8241. Min Act: -0.0000

Data Index: 779311 (C4 (Web Text))

Max Activating Token Index: 153