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

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

Neuron 2044 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: 0.1144. Min Range: -0.1144

Max Act: 0.1115. Min Act: -0.0002

Data Index: 152443 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1144. Min Act: -0.0002

Data Index: 543348 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1043. Min Act: -0.0002

Data Index: 1343234 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1068. Min Act: -0.0002

Data Index: 1020316 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1056. Min Act: -0.0002

Data Index: 123443 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1006. Min Act: -0.0002

Data Index: 1028969 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1167690 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1032. Min Act: -0.0002

Data Index: 1352024 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1041. Min Act: -0.0002

Data Index: 902846 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0998. Min Act: -0.0002

Data Index: 473756 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0998. Min Act: -0.0002

Data Index: 1287032 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0970. Min Act: -0.0002

Data Index: 327706 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0981. Min Act: -0.0002

Data Index: 200456 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1038. Min Act: -0.0002

Data Index: 1120098 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0967. Min Act: -0.0002

Data Index: 166763 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1100212 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1047. Min Act: -0.0002

Data Index: 815899 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0965. Min Act: -0.0002

Data Index: 645745 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0969. Min Act: -0.0002

Data Index: 290630 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0966. Min Act: -0.0002

Data Index: 430733 (C4 (Web Text))

Max Activating Token Index: 203