Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1632 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1130. Min Act: -0.0002

Data Index: 246329 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1101. Min Act: -0.0002

Data Index: 594376 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1115. Min Act: 0.0002

Data Index: 1141467 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1112. Min Act: -0.0002

Data Index: 570149 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1098. Min Act: -0.0001

Data Index: 1051750 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1088. Min Act: -0.0002

Data Index: 448280 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1055. Min Act: -0.0002

Data Index: 569271 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1033. Min Act: -0.0001

Data Index: 1255217 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1047. Min Act: -0.0002

Data Index: 601445 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1045. Min Act: -0.0001

Data Index: 426757 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1041. Min Act: -0.0002

Data Index: 134892 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1019. Min Act: -0.0002

Data Index: 158172 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1023. Min Act: -0.0002

Data Index: 133948 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1042. Min Act: -0.0001

Data Index: 760438 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1018. Min Act: -0.0001

Data Index: 296144 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1019. Min Act: -0.0001

Data Index: 479807 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1250485 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1013. Min Act: 0.0000

Data Index: 646756 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1344211 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0979. Min Act: -0.0002

Data Index: 540870 (C4 (Web Text))

Max Activating Token Index: 255