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

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

Neuron 3776 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: 1.9722. Min Range: -1.9722

Max Act: 1.9722. Min Act: -0.0002

Data Index: 449067 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.8009. Min Act: -0.0002

Data Index: 881626 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.5388. Min Act: -0.0002

Data Index: 46757 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.5661. Min Act: -0.0002

Data Index: 1052289 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.4754. Min Act: -0.0002

Data Index: 800744 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.5652. Min Act: -0.0002

Data Index: 1113434 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.3631. Min Act: -0.0002

Data Index: 393466 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.4101. Min Act: -0.0002

Data Index: 1203596 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.2670. Min Act: -0.0002

Data Index: 340007 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.5294. Min Act: -0.0002

Data Index: 538835 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.3972. Min Act: -0.0002

Data Index: 832169 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.2109. Min Act: -0.0002

Data Index: 656328 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.1986. Min Act: -0.0002

Data Index: 1328417 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.2953. Min Act: -0.0002

Data Index: 1163939 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.2523. Min Act: -0.0002

Data Index: 936080 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.2569. Min Act: -0.0002

Data Index: 546686 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.1656. Min Act: -0.0002

Data Index: 509667 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.2538. Min Act: -0.0002

Data Index: 1251179 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.3161. Min Act: -0.0002

Data Index: 1011114 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 1.9722. Min Range: -1.9722

Max Act: 1.2283. Min Act: -0.0002

Data Index: 42390 (C4 (Web Text))

Max Activating Token Index: 972