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

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

Neuron 4979 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: 0.2386. Min Range: -0.2386

Max Act: 0.2386. Min Act: -0.0000

Data Index: 226290 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2208. Min Act: -0.0000

Data Index: 665331 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2166. Min Act: -0.0000

Data Index: 352997 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2309. Min Act: -0.0000

Data Index: 462998 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2023. Min Act: -0.0000

Data Index: 899560 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2078. Min Act: -0.0000

Data Index: 709706 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2283. Min Act: -0.0000

Data Index: 1239981 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2238. Min Act: -0.0000

Data Index: 880246 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2220. Min Act: -0.0000

Data Index: 911004 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2172. Min Act: -0.0000

Data Index: 251757 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1119886 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2355. Min Act: -0.0000

Data Index: 359827 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2069. Min Act: -0.0000

Data Index: 161827 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2262. Min Act: -0.0000

Data Index: 266127 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2019. Min Act: -0.0000

Data Index: 52272 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2115. Min Act: -0.0000

Data Index: 689790 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2009. Min Act: -0.0000

Data Index: 359940 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1973. Min Act: -0.0000

Data Index: 287784 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2109. Min Act: -0.0000

Data Index: 554923 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2051. Min Act: -0.0000

Data Index: 72644 (C4 (Web Text))

Max Activating Token Index: 182