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

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

Neuron 973 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: 2.1166. Min Range: -2.1166

Max Act: 2.1166. Min Act: -0.0000

Data Index: 997302 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 2.1166. Min Range: -2.1166

Max Act: 1.5119. Min Act: -0.0000

Data Index: 413053 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 2.1166. Min Range: -2.1166

Max Act: 1.5066. Min Act: -0.0000

Data Index: 321908 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 2.1166. Min Range: -2.1166

Max Act: 1.3118. Min Act: -0.0000

Data Index: 226248 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 2.1166. Min Range: -2.1166

Max Act: 1.2416. Min Act: -0.0000

Data Index: 833062 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 2.1166. Min Range: -2.1166

Max Act: 1.2181. Min Act: -0.0000

Data Index: 1222803 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 2.1166. Min Range: -2.1166

Max Act: 1.1242. Min Act: -0.0000

Data Index: 127653 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 2.1166. Min Range: -2.1166

Max Act: 1.0793. Min Act: -0.0000

Data Index: 321711 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 2.1166. Min Range: -2.1166

Max Act: 1.0713. Min Act: -0.0000

Data Index: 306279 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 2.1166. Min Range: -2.1166

Max Act: 1.0532. Min Act: -0.0000

Data Index: 36212 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 2.1166. Min Range: -2.1166

Max Act: 0.9924. Min Act: -0.0000

Data Index: 280006 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 2.1166. Min Range: -2.1166

Max Act: 1.0357. Min Act: -0.0000

Data Index: 724089 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 2.1166. Min Range: -2.1166

Max Act: 1.0006. Min Act: -0.0000

Data Index: 137079 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 2.1166. Min Range: -2.1166

Max Act: 1.0268. Min Act: -0.0000

Data Index: 610582 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 2.1166. Min Range: -2.1166

Max Act: 1.0409. Min Act: -0.0000

Data Index: 317493 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 2.1166. Min Range: -2.1166

Max Act: 0.9841. Min Act: -0.0000

Data Index: 1233448 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 2.1166. Min Range: -2.1166

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1290647 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 2.1166. Min Range: -2.1166

Max Act: 0.9998. Min Act: -0.0000

Data Index: 1173012 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 2.1166. Min Range: -2.1166

Max Act: 0.9682. Min Act: -0.0000

Data Index: 488103 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 2.1166. Min Range: -2.1166

Max Act: 0.8686. Min Act: -0.0000

Data Index: 322748 (C4 (Web Text))

Max Activating Token Index: 994