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

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

Neuron 1375 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.2496. Min Act: -0.0000

Data Index: 712251 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.2463. Min Act: -0.0000

Data Index: 241678 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.2383. Min Act: -0.0000

Data Index: 851455 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.2145. Min Act: -0.0000

Data Index: 624870 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.2177. Min Act: -0.0000

Data Index: 503495 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.2078. Min Act: -0.0000

Data Index: 149736 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1999. Min Act: -0.0000

Data Index: 170953 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.2004. Min Act: -0.0000

Data Index: 856603 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1957. Min Act: -0.0000

Data Index: 584401 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1927. Min Act: -0.0000

Data Index: 158559 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1910. Min Act: -0.0000

Data Index: 687936 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1902. Min Act: -0.0000

Data Index: 181230 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1829. Min Act: -0.0000

Data Index: 964104 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1283673 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1322816 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1158500 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1713. Min Act: -0.0000

Data Index: 866050 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1737. Min Act: 0.0000

Data Index: 152314 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1783. Min Act: -0.0000

Data Index: 991740 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1739. Min Act: -0.0000

Data Index: 233262 (C4 (Web Text))

Max Activating Token Index: 454