Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 561 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8202. Min Range: -2.8202

Max Act: 2.8202. Min Act: -0.0000

Data Index: 468879 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 2.8202. Min Range: -2.8202

Max Act: 2.5144. Min Act: -0.0000

Data Index: 1278034 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 2.8202. Min Range: -2.8202

Max Act: 2.4466. Min Act: -0.0000

Data Index: 538328 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 2.8202. Min Range: -2.8202

Max Act: 2.1356. Min Act: -0.0000

Data Index: 317384 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 2.8202. Min Range: -2.8202

Max Act: 2.2209. Min Act: -0.0000

Data Index: 700265 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 2.8202. Min Range: -2.8202

Max Act: 2.1241. Min Act: -0.0000

Data Index: 46871 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 2.8202. Min Range: -2.8202

Max Act: 2.1010. Min Act: -0.0000

Data Index: 571595 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 2.8202. Min Range: -2.8202

Max Act: 2.2090. Min Act: -0.0000

Data Index: 55482 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 2.8202. Min Range: -2.8202

Max Act: 2.0194. Min Act: -0.0000

Data Index: 321780 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 2.8202. Min Range: -2.8202

Max Act: 2.2235. Min Act: -0.0000

Data Index: 432806 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 2.8202. Min Range: -2.8202

Max Act: 2.0085. Min Act: -0.0000

Data Index: 888967 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 2.8202. Min Range: -2.8202

Max Act: 1.9550. Min Act: -0.0000

Data Index: 960008 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 2.8202. Min Range: -2.8202

Max Act: 2.0306. Min Act: -0.0000

Data Index: 1188839 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 2.8202. Min Range: -2.8202

Max Act: 1.9393. Min Act: -0.0000

Data Index: 932903 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 2.8202. Min Range: -2.8202

Max Act: 2.0252. Min Act: -0.0000

Data Index: 535670 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 2.8202. Min Range: -2.8202

Max Act: 1.8183. Min Act: -0.0000

Data Index: 1092720 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 2.8202. Min Range: -2.8202

Max Act: 1.8851. Min Act: -0.0000

Data Index: 823384 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 2.8202. Min Range: -2.8202

Max Act: 1.8495. Min Act: -0.0000

Data Index: 97637 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 2.8202. Min Range: -2.8202

Max Act: 1.8663. Min Act: -0.0000

Data Index: 886985 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 2.8202. Min Range: -2.8202

Max Act: 1.8240. Min Act: -0.0000

Data Index: 988740 (C4 (Web Text))

Max Activating Token Index: 365