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

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

Neuron 1313 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.6102. Min Act: -0.0000

Data Index: 1012845 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.4853. Min Act: -0.0000

Data Index: 13066 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.4202. Min Act: -0.0000

Data Index: 334002 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.2321. Min Act: -0.0000

Data Index: 363178 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.2222. Min Act: -0.0000

Data Index: 816164 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.1976. Min Act: -0.0000

Data Index: 425721 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1117159 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1004364 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.0403. Min Act: -0.0000

Data Index: 727521 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.0951. Min Act: -0.0000

Data Index: 126906 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 1.6102. Min Range: -1.6102

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1178081 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.0201. Min Act: -0.0000

Data Index: 810251 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.0615. Min Act: -0.0000

Data Index: 1214226 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 1.6102. Min Range: -1.6102

Max Act: 0.9401. Min Act: -0.0000

Data Index: 289235 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.0820. Min Act: -0.0000

Data Index: 980155 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 1.6102. Min Range: -1.6102

Max Act: 0.9558. Min Act: -0.0000

Data Index: 398388 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.0137. Min Act: -0.0000

Data Index: 324516 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 1.6102. Min Range: -1.6102

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1072435 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.0033. Min Act: -0.0000

Data Index: 1210359 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 1.6102. Min Range: -1.6102

Max Act: 0.9401. Min Act: -0.0000

Data Index: 1065562 (C4 (Web Text))

Max Activating Token Index: 920