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

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

Neuron 50 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: 1.1911. Min Range: -1.1911

Max Act: 1.1911. Min Act: -0.0000

Data Index: 1001250 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1176149 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.7431. Min Act: -0.0000

Data Index: 256620 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.7727. Min Act: -0.0000

Data Index: 1348013 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.7377. Min Act: -0.0000

Data Index: 1352951 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.5796. Min Act: -0.0000

Data Index: 138905 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.6272. Min Act: -0.0000

Data Index: 226957 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.6368. Min Act: -0.0000

Data Index: 185225 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.6516. Min Act: -0.0000

Data Index: 560081 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.5646. Min Act: -0.0000

Data Index: 311946 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1114998 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.6246. Min Act: -0.0000

Data Index: 408931 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1601779 (Python Code)

Max Activating Token Index: 98

Text #13

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.6415. Min Act: -0.0000

Data Index: 673649 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.6189. Min Act: -0.0000

Data Index: 256155 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.5904. Min Act: -0.0000

Data Index: 647065 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1298431 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.6666. Min Act: -0.0000

Data Index: 49589 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.6012. Min Act: -0.0000

Data Index: 400553 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.5875. Min Act: -0.0000

Data Index: 887795 (C4 (Web Text))

Max Activating Token Index: 780