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

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

Neuron 1578 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.8546. Min Act: -0.0000

Data Index: 81102 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.5444. Min Act: -0.0000

Data Index: 655161 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.5933. Min Act: -0.0000

Data Index: 838736 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.5677. Min Act: -0.0000

Data Index: 719033 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.6105. Min Act: -0.0000

Data Index: 857109 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.3812. Min Act: -0.0000

Data Index: 1274262 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.3660. Min Act: -0.0000

Data Index: 844885 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.4346. Min Act: -0.0000

Data Index: 132920 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.5037. Min Act: -0.0000

Data Index: 1234201 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.3992. Min Act: -0.0000

Data Index: 1204732 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.3099. Min Act: -0.0000

Data Index: 721080 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.3761. Min Act: -0.0000

Data Index: 1002021 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.4408. Min Act: -0.0000

Data Index: 447384 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.4023. Min Act: -0.0000

Data Index: 439541 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.3264. Min Act: -0.0000

Data Index: 1288512 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.2812. Min Act: -0.0000

Data Index: 688402 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.1395. Min Act: -0.0000

Data Index: 207491 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.2725. Min Act: -0.0000

Data Index: 385484 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.2715. Min Act: -0.0000

Data Index: 1203399 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 1.8546. Min Range: -1.8546

Max Act: 1.2684. Min Act: -0.0000

Data Index: 977308 (C4 (Web Text))

Max Activating Token Index: 223