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

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

Neuron 3635 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: 0.6144. Min Range: -0.6144

Max Act: 0.5785. Min Act: -0.0000

Data Index: 369938 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.6144. Min Act: -0.0000

Data Index: 69773 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1318393 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5283. Min Act: -0.0000

Data Index: 249274 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5195. Min Act: -0.0000

Data Index: 904547 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5418. Min Act: -0.0000

Data Index: 109569 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4891. Min Act: -0.0000

Data Index: 959648 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4723. Min Act: -0.0000

Data Index: 567887 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1239611 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4823. Min Act: -0.0000

Data Index: 717888 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5019. Min Act: -0.0000

Data Index: 1237615 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4733. Min Act: -0.0000

Data Index: 928655 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4838. Min Act: -0.0000

Data Index: 1142665 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4387. Min Act: -0.0000

Data Index: 602762 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4333. Min Act: -0.0000

Data Index: 525725 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4468. Min Act: -0.0000

Data Index: 78725 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1117200 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4242. Min Act: -0.0000

Data Index: 1350614 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1221051 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1290396 (C4 (Web Text))

Max Activating Token Index: 703