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

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

Neuron 472 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: 1.2235. Min Range: -1.2235

Max Act: 1.2235. Min Act: -0.0000

Data Index: 449019 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1087145 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 1.2235. Min Range: -1.2235

Max Act: 1.1296. Min Act: -0.0000

Data Index: 96909 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 1.2235. Min Range: -1.2235

Max Act: 1.1650. Min Act: -0.0000

Data Index: 931806 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 1.2235. Min Range: -1.2235

Max Act: 1.1311. Min Act: -0.0000

Data Index: 720464 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 1.2235. Min Range: -1.2235

Max Act: 1.0360. Min Act: -0.0000

Data Index: 758230 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.9753. Min Act: -0.0000

Data Index: 140022 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 1.2235. Min Range: -1.2235

Max Act: 1.0338. Min Act: -0.0000

Data Index: 342228 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.9212. Min Act: -0.0000

Data Index: 973182 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 1.2235. Min Range: -1.2235

Max Act: 1.0687. Min Act: -0.0000

Data Index: 238677 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.9953. Min Act: -0.0000

Data Index: 212948 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 1.2235. Min Range: -1.2235

Max Act: 1.0044. Min Act: -0.0000

Data Index: 46440 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.9620. Min Act: -0.0000

Data Index: 690858 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.9327. Min Act: -0.0000

Data Index: 883418 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 1.2235. Min Range: -1.2235

Max Act: 1.0805. Min Act: -0.0000

Data Index: 932192 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.9631. Min Act: -0.0000

Data Index: 730600 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 1.2235. Min Range: -1.2235

Max Act: 1.0208. Min Act: -0.0000

Data Index: 1401157 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.9508. Min Act: -0.0000

Data Index: 194832 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 1.2235. Min Range: -1.2235

Max Act: 1.1310. Min Act: -0.0000

Data Index: 1164897 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 1.2235. Min Range: -1.2235

Max Act: 1.0509. Min Act: -0.0000

Data Index: 103289 (C4 (Web Text))

Max Activating Token Index: 684