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

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

Neuron 4574 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.7025. Min Act: -0.0002

Data Index: 1233462 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6329. Min Act: -0.0002

Data Index: 327674 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6512. Min Act: -0.0002

Data Index: 890224 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5838. Min Act: -0.0002

Data Index: 1028747 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6568. Min Act: -0.0002

Data Index: 1010935 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5196. Min Act: -0.0002

Data Index: 259016 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.7164. Min Act: -0.0002

Data Index: 1339497 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6305. Min Act: -0.0002

Data Index: 370885 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5627. Min Act: -0.0002

Data Index: 793212 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5868. Min Act: -0.0002

Data Index: 982535 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5610. Min Act: -0.0002

Data Index: 1289618 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5796. Min Act: -0.0002

Data Index: 924091 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6408. Min Act: -0.0002

Data Index: 1122099 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5945. Min Act: -0.0002

Data Index: 600128 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6245. Min Act: -0.0002

Data Index: 342953 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5820. Min Act: -0.0002

Data Index: 892846 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5726. Min Act: -0.0002

Data Index: 1032858 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5850. Min Act: -0.0002

Data Index: 1218437 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6106. Min Act: -0.0002

Data Index: 858170 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5820. Min Act: -0.0002

Data Index: 186018 (C4 (Web Text))

Max Activating Token Index: 465