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

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

Neuron 1016 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.6992. Min Act: -0.0001

Data Index: 948499 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5986. Min Act: -0.0001

Data Index: 1194570 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5583. Min Act: -0.0001

Data Index: 1455953 (Python Code)

Max Activating Token Index: 61

Text #3

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5855. Min Act: -0.0001

Data Index: 985914 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.6487. Min Act: -0.0001

Data Index: 507354 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.6079. Min Act: -0.0001

Data Index: 9446 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5804. Min Act: -0.0001

Data Index: 198258 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5739. Min Act: -0.0001

Data Index: 414061 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.6053. Min Act: -0.0001

Data Index: 384331 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.6085. Min Act: -0.0001

Data Index: 824971 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5569. Min Act: -0.0001

Data Index: 473133 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.6488. Min Act: -0.0001

Data Index: 1138327 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.6500. Min Act: -0.0001

Data Index: 279325 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5914. Min Act: -0.0001

Data Index: 1072314 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.4990. Min Act: -0.0001

Data Index: 1272550 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5242. Min Act: -0.0001

Data Index: 121946 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5141. Min Act: -0.0001

Data Index: 1204946 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5811. Min Act: -0.0001

Data Index: 147948 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5259. Min Act: -0.0001

Data Index: 1145103 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.6992. Min Range: -0.6992

Max Act: 0.5655. Min Act: -0.0001

Data Index: 1281337 (C4 (Web Text))

Max Activating Token Index: 539