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

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

Neuron 3779 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: 1.6054. Min Range: -1.6054

Max Act: 1.6054. Min Act: -0.0000

Data Index: 932033 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4288. Min Act: -0.0000

Data Index: 662769 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.1929. Min Act: -0.0000

Data Index: 1279658 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.1881. Min Act: -0.0000

Data Index: 461253 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.2338. Min Act: -0.0000

Data Index: 1179834 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.2511. Min Act: -0.0000

Data Index: 940284 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0772. Min Act: -0.0000

Data Index: 943557 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.2079. Min Act: -0.0000

Data Index: 1300848 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.1640. Min Act: -0.0000

Data Index: 1340180 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.1350. Min Act: -0.0000

Data Index: 475871 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0807. Min Act: -0.0000

Data Index: 352145 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.1217. Min Act: -0.0000

Data Index: 33975 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0394. Min Act: -0.0000

Data Index: 1283220 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0782. Min Act: -0.0000

Data Index: 1042727 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9807. Min Act: -0.0000

Data Index: 129143 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9986. Min Act: -0.0000

Data Index: 316530 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0074. Min Act: -0.0000

Data Index: 703165 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0068. Min Act: -0.0000

Data Index: 393879 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9763. Min Act: -0.0000

Data Index: 1099317 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9745. Min Act: -0.0000

Data Index: 26633 (C4 (Web Text))

Max Activating Token Index: 1016