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

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

Neuron 3164 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: 1.0225. Min Range: -1.0225

Max Act: 1.0225. Min Act: -0.0000

Data Index: 810921 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.9317. Min Act: -0.0000

Data Index: 1275681 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.8914. Min Act: -0.0000

Data Index: 117959 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.7559. Min Act: -0.0000

Data Index: 13414 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.8208. Min Act: -0.0000

Data Index: 445258 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1277726 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.7335. Min Act: -0.0000

Data Index: 797523 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1350264 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.7112. Min Act: -0.0000

Data Index: 1065843 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.7539. Min Act: -0.0000

Data Index: 367334 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.7564. Min Act: -0.0000

Data Index: 956498 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.7719. Min Act: -0.0000

Data Index: 641356 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.6872. Min Act: -0.0000

Data Index: 123859 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1230833 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.7212. Min Act: -0.0000

Data Index: 176208 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.6397. Min Act: -0.0000

Data Index: 664434 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.6563. Min Act: -0.0000

Data Index: 658057 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.6421. Min Act: -0.0000

Data Index: 1114421 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.6455. Min Act: -0.0000

Data Index: 339337 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 1.0225. Min Range: -1.0225

Max Act: 0.6080. Min Act: -0.0000

Data Index: 1195953 (C4 (Web Text))

Max Activating Token Index: 90