Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 882 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.9286. Min Act: -0.0002

Data Index: 1203834 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.8473. Min Act: -0.0002

Data Index: 1049836 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.7587. Min Act: -0.0002

Data Index: 745657 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.7276. Min Act: -0.0002

Data Index: 366707 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.7344. Min Act: -0.0002

Data Index: 228748 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.7314. Min Act: -0.0002

Data Index: 975338 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.7154. Min Act: -0.0002

Data Index: 516772 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.6618. Min Act: -0.0002

Data Index: 435482 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.6771. Min Act: -0.0002

Data Index: 25823 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.7041. Min Act: -0.0002

Data Index: 849662 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.6792. Min Act: -0.0002

Data Index: 621812 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.6292. Min Act: -0.0002

Data Index: 575714 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.6497. Min Act: -0.0002

Data Index: 907654 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.6015. Min Act: -0.0002

Data Index: 534966 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.5976. Min Act: -0.0002

Data Index: 613089 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.6353. Min Act: -0.0002

Data Index: 270070 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.6061. Min Act: -0.0002

Data Index: 892297 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.6153. Min Act: -0.0002

Data Index: 749781 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.5629. Min Act: -0.0002

Data Index: 136986 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.9286. Min Range: -0.9286

Max Act: 0.6043. Min Act: -0.0002

Data Index: 833388 (C4 (Web Text))

Max Activating Token Index: 127