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

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

Neuron 1820 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: 0.3676. Min Range: -0.3676

Max Act: 0.3676. Min Act: -0.0000

Data Index: 629558 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2965. Min Act: -0.0000

Data Index: 478693 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2984. Min Act: -0.0000

Data Index: 950775 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2977. Min Act: -0.0000

Data Index: 594848 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2870. Min Act: -0.0000

Data Index: 689720 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.3040. Min Act: -0.0000

Data Index: 93660 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2775. Min Act: -0.0000

Data Index: 830269 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2876. Min Act: -0.0000

Data Index: 116695 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2744. Min Act: -0.0000

Data Index: 961518 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2701. Min Act: -0.0000

Data Index: 174918 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2579. Min Act: -0.0000

Data Index: 818878 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1311193 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2620. Min Act: -0.0000

Data Index: 475857 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2504. Min Act: -0.0000

Data Index: 854245 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2594. Min Act: -0.0000

Data Index: 1329974 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2535. Min Act: -0.0000

Data Index: 466994 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1351650 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2584. Min Act: -0.0000

Data Index: 810334 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2516. Min Act: -0.0000

Data Index: 175810 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.3676. Min Range: -0.3676

Max Act: 0.2597. Min Act: -0.0000

Data Index: 261238 (C4 (Web Text))

Max Activating Token Index: 548