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

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

Neuron 2349 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: 0.3046. Min Range: -0.3046

Max Act: 0.3046. Min Act: -0.0000

Data Index: 722948 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2798. Min Act: -0.0000

Data Index: 918290 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2646. Min Act: -0.0000

Data Index: 99121 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1280070 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1165334 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2295. Min Act: -0.0000

Data Index: 738186 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2237. Min Act: -0.0000

Data Index: 252011 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2165. Min Act: -0.0000

Data Index: 194081 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2012. Min Act: -0.0000

Data Index: 78315 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.1971. Min Act: -0.0000

Data Index: 788796 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.1968. Min Act: -0.0000

Data Index: 656849 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.1897. Min Act: -0.0000

Data Index: 328277 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.2022. Min Act: -0.0000

Data Index: 196340 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.1944. Min Act: -0.0000

Data Index: 344839 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.1844. Min Act: -0.0000

Data Index: 1144842 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.1838. Min Act: -0.0000

Data Index: 941635 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.1824. Min Act: -0.0000

Data Index: 315717 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.1962. Min Act: -0.0000

Data Index: 18645 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1282026 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 0.3046. Min Range: -0.3046

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1129906 (C4 (Web Text))

Max Activating Token Index: 229