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

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

Neuron 32 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: 0.8505. Min Range: -0.8505

Max Act: 0.8455. Min Act: -0.0000

Data Index: 89390 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.8502. Min Act: -0.0000

Data Index: 53225 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.8505. Min Act: -0.0000

Data Index: 149564 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.8460. Min Act: -0.0000

Data Index: 805998 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.8401. Min Act: -0.0000

Data Index: 697965 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7432. Min Act: -0.0000

Data Index: 703268 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7143. Min Act: -0.0000

Data Index: 820424 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1275807 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7368. Min Act: -0.0000

Data Index: 1170830 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6703. Min Act: -0.0000

Data Index: 51719 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6759. Min Act: 0.0000

Data Index: 1063391 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6982. Min Act: -0.0000

Data Index: 470799 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5853. Min Act: -0.0000

Data Index: 740822 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6399. Min Act: 0.0001

Data Index: 1236955 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5906. Min Act: -0.0000

Data Index: 825746 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5679. Min Act: -0.0000

Data Index: 569966 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5814. Min Act: -0.0000

Data Index: 582397 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5823. Min Act: -0.0000

Data Index: 122233 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5588. Min Act: -0.0000

Data Index: 562045 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5746. Min Act: -0.0000

Data Index: 600411 (C4 (Web Text))

Max Activating Token Index: 257