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

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

Neuron 5907 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1228. Min Act: -0.0002

Data Index: 1228457 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1044. Min Act: -0.0002

Data Index: 204886 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0983. Min Act: -0.0002

Data Index: 100871 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1010. Min Act: -0.0002

Data Index: 1291850 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0976. Min Act: -0.0002

Data Index: 470958 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1030. Min Act: -0.0002

Data Index: 1082977 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0997. Min Act: -0.0002

Data Index: 192680 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0978. Min Act: -0.0002

Data Index: 213556 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0935. Min Act: -0.0002

Data Index: 189450 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0971. Min Act: -0.0002

Data Index: 1291439 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1048071 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0914. Min Act: -0.0002

Data Index: 475136 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1179264 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0908. Min Act: -0.0002

Data Index: 1289329 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1217372 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0872. Min Act: -0.0002

Data Index: 1286475 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1094893 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1016718 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0891. Min Act: -0.0002

Data Index: 61735 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0891. Min Act: -0.0002

Data Index: 496352 (C4 (Web Text))

Max Activating Token Index: 72