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

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

Neuron 2104 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: 0.2726. Min Range: -0.2726

Max Act: 0.2726. Min Act: -0.0000

Data Index: 177748 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2309. Min Act: -0.0000

Data Index: 915869 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2332. Min Act: -0.0000

Data Index: 267983 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2391. Min Act: -0.0000

Data Index: 336049 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2186. Min Act: -0.0000

Data Index: 749731 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2069. Min Act: -0.0000

Data Index: 942215 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1318997 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2004. Min Act: -0.0000

Data Index: 1371196 (Python Code)

Max Activating Token Index: 274

Text #8

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2102. Min Act: -0.0000

Data Index: 688181 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2078. Min Act: -0.0000

Data Index: 95310 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1082851 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1246810 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2062. Min Act: -0.0000

Data Index: 14579 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1044665 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1031547 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1609682 (Python Code)

Max Activating Token Index: 975

Text #16

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1803. Min Act: -0.0000

Data Index: 470981 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1865. Min Act: -0.0000

Data Index: 156426 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1792. Min Act: -0.0000

Data Index: 626105 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1322843 (C4 (Web Text))

Max Activating Token Index: 768