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

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

Neuron 815 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: 1.2109. Min Range: -1.2109

Max Act: 1.2109. Min Act: -0.0001

Data Index: 1447383 (Python Code)

Max Activating Token Index: 1010

Text #1

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.7854. Min Act: -0.0001

Data Index: 761383 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.9097. Min Act: -0.0001

Data Index: 5097 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.8591. Min Act: -0.0001

Data Index: 565288 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.7286. Min Act: -0.0001

Data Index: 840422 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.6902. Min Act: -0.0001

Data Index: 229483 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.6199. Min Act: -0.0001

Data Index: 1301204 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.7733. Min Act: -0.0001

Data Index: 329065 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.6270. Min Act: -0.0001

Data Index: 1450049 (Python Code)

Max Activating Token Index: 877

Text #9

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.6232. Min Act: -0.0001

Data Index: 337092 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.5907. Min Act: -0.0001

Data Index: 1638285 (Python Code)

Max Activating Token Index: 217

Text #11

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.5480. Min Act: -0.0001

Data Index: 1553209 (Python Code)

Max Activating Token Index: 111

Text #12

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.5489. Min Act: -0.0001

Data Index: 1128260 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.6009. Min Act: -0.0001

Data Index: 304864 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.6163. Min Act: -0.0001

Data Index: 1530285 (Python Code)

Max Activating Token Index: 991

Text #15

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.6447. Min Act: -0.0001

Data Index: 757086 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.6032. Min Act: -0.0001

Data Index: 1002664 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.4567. Min Act: -0.0001

Data Index: 1392627 (Python Code)

Max Activating Token Index: 575

Text #18

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.5756. Min Act: -0.0001

Data Index: 161561 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.5007. Min Act: -0.0001

Data Index: 1469001 (Python Code)

Max Activating Token Index: 962