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

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

Neuron 3820 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: 1.4688. Min Range: -1.4688

Max Act: 1.4688. Min Act: -0.0000

Data Index: 635819 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 1.4688. Min Range: -1.4688

Max Act: 1.2150. Min Act: -0.0000

Data Index: 624398 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 1.4688. Min Range: -1.4688

Max Act: 1.0797. Min Act: -0.0000

Data Index: 818173 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 1.4688. Min Range: -1.4688

Max Act: 1.0506. Min Act: -0.0000

Data Index: 440696 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 1.4688. Min Range: -1.4688

Max Act: 1.0464. Min Act: -0.0000

Data Index: 794441 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 1.4688. Min Range: -1.4688

Max Act: 1.1220. Min Act: -0.0000

Data Index: 362590 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.9511. Min Act: -0.0000

Data Index: 892620 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.8755. Min Act: -0.0000

Data Index: 851264 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.8725. Min Act: -0.0000

Data Index: 561720 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.8816. Min Act: -0.0000

Data Index: 157000 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.8767. Min Act: -0.0000

Data Index: 171562 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.8248. Min Act: -0.0000

Data Index: 292542 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1223921 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.8556. Min Act: -0.0000

Data Index: 506995 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.8434. Min Act: -0.0000

Data Index: 848546 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.8163. Min Act: -0.0000

Data Index: 942215 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.8435. Min Act: -0.0000

Data Index: 612405 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.9207. Min Act: -0.0000

Data Index: 3205 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.8619. Min Act: -0.0000

Data Index: 782085 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.8530. Min Act: -0.0000

Data Index: 1017332 (C4 (Web Text))

Max Activating Token Index: 329