Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1500 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1447. Min Act: -0.0001

Data Index: 912480 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1352. Min Act: -0.0001

Data Index: 988771 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1366. Min Act: -0.0001

Data Index: 728941 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1255. Min Act: -0.0001

Data Index: 97893 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1217. Min Act: -0.0001

Data Index: 101432 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1193. Min Act: -0.0000

Data Index: 596327 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1129342 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1160. Min Act: -0.0001

Data Index: 718786 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1118. Min Act: -0.0001

Data Index: 25532 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1108. Min Act: -0.0001

Data Index: 997759 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1111. Min Act: -0.0001

Data Index: 792022 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1023735 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1343808 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1055. Min Act: -0.0001

Data Index: 445394 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.0978. Min Act: -0.0001

Data Index: 444139 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1047. Min Act: -0.0000

Data Index: 912663 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1044. Min Act: -0.0001

Data Index: 1049841 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1090056 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1006. Min Act: -0.0001

Data Index: 954504 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1028. Min Act: -0.0001

Data Index: 356772 (C4 (Web Text))

Max Activating Token Index: 874