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

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

Neuron 811 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5416. Min Act: -0.0001

Data Index: 1115434 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.6459. Min Act: -0.0001

Data Index: 714732 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.6106. Min Act: -0.0001

Data Index: 582166 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.6379. Min Act: -0.0001

Data Index: 35845 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5876. Min Act: -0.0001

Data Index: 193661 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.6169. Min Act: -0.0001

Data Index: 477797 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.6081. Min Act: -0.0001

Data Index: 89492 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5220. Min Act: -0.0001

Data Index: 1175667 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5811. Min Act: -0.0001

Data Index: 879409 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5823. Min Act: -0.0001

Data Index: 664524 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5584. Min Act: -0.0001

Data Index: 1175583 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5418. Min Act: -0.0001

Data Index: 547107 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5899. Min Act: -0.0001

Data Index: 22176 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5398. Min Act: -0.0001

Data Index: 767400 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.4820. Min Act: -0.0001

Data Index: 471903 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.4296. Min Act: -0.0001

Data Index: 836732 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5487. Min Act: -0.0001

Data Index: 1088422 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5427. Min Act: -0.0001

Data Index: 68521 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5051. Min Act: -0.0001

Data Index: 606477 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5575. Min Act: -0.0001

Data Index: 32527 (C4 (Web Text))

Max Activating Token Index: 311