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

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

Neuron 4853 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: 0.1368. Min Range: -0.1368

Max Act: 0.1368. Min Act: -0.0001

Data Index: 290403 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1208. Min Act: -0.0001

Data Index: 64582 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1124. Min Act: -0.0001

Data Index: 232285 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1099229 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1082. Min Act: -0.0001

Data Index: 57041 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1031. Min Act: -0.0001

Data Index: 979991 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1047. Min Act: -0.0001

Data Index: 469592 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1095623 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1614093 (Python Code)

Max Activating Token Index: 117

Text #9

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1537588 (Python Code)

Max Activating Token Index: 213

Text #10

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1595195 (Python Code)

Max Activating Token Index: 107

Text #11

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1337228 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0950. Min Act: -0.0001

Data Index: 616301 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0996. Min Act: -0.0001

Data Index: 812674 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0887. Min Act: -0.0001

Data Index: 988965 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1191387 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0918. Min Act: -0.0001

Data Index: 702363 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1016. Min Act: -0.0001

Data Index: 74692 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1455053 (Python Code)

Max Activating Token Index: 64

Text #19

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0959. Min Act: -0.0001

Data Index: 129834 (C4 (Web Text))

Max Activating Token Index: 924