Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3039 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.6078. Min Act: -0.0003

Data Index: 1351636 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.6127. Min Act: -0.0003

Data Index: 273212 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4977. Min Act: -0.0003

Data Index: 179386 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4443. Min Act: -0.0003

Data Index: 591588 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4369. Min Act: -0.0003

Data Index: 1354110 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4934. Min Act: -0.0003

Data Index: 1158730 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4664. Min Act: -0.0003

Data Index: 539776 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4385. Min Act: -0.0003

Data Index: 828477 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4507. Min Act: -0.0003

Data Index: 81910 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4451. Min Act: -0.0003

Data Index: 1070495 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4155. Min Act: -0.0003

Data Index: 976996 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4695. Min Act: -0.0003

Data Index: 1322360 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4652. Min Act: -0.0003

Data Index: 1123665 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4222. Min Act: -0.0003

Data Index: 684661 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4303. Min Act: -0.0003

Data Index: 203305 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4442. Min Act: -0.0003

Data Index: 1075642 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4024. Min Act: -0.0003

Data Index: 797867 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4152. Min Act: -0.0003

Data Index: 41797 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4420. Min Act: -0.0003

Data Index: 83683 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.6127. Min Range: -0.6127

Max Act: 0.4142. Min Act: -0.0003

Data Index: 1055968 (C4 (Web Text))

Max Activating Token Index: 700