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

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

Neuron 990 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.9886. Min Act: -0.0000

Data Index: 1049784 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.5392. Min Act: -0.0000

Data Index: 240268 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.8370. Min Act: -0.0000

Data Index: 1074823 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.4277. Min Act: -0.0000

Data Index: 1174000 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.5595. Min Act: -0.0000

Data Index: 921146 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.3436. Min Act: -0.0000

Data Index: 1248336 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.2656. Min Act: -0.0000

Data Index: 173096 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.4125. Min Act: -0.0000

Data Index: 168595 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.3484. Min Act: -0.0000

Data Index: 1359728 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.2248. Min Act: -0.0000

Data Index: 58768 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.3071. Min Act: -0.0000

Data Index: 919485 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.1618. Min Act: -0.0000

Data Index: 964543 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.0559. Min Act: -0.0000

Data Index: 1301940 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.0180. Min Act: -0.0000

Data Index: 1308643 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.1358. Min Act: -0.0000

Data Index: 543403 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.9794. Min Act: -0.0000

Data Index: 683208 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.1158. Min Act: -0.0000

Data Index: 1031939 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.9765. Min Act: -0.0000

Data Index: 915793 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.0603. Min Act: -0.0000

Data Index: 580053 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.9797. Min Act: -0.0000

Data Index: 1012692 (C4 (Web Text))

Max Activating Token Index: 270