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

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

Neuron 17 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: 0.1174. Min Range: -0.1174

Max Act: 0.1174. Min Act: -0.0002

Data Index: 1219929 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1099. Min Act: -0.0001

Data Index: 994636 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1038. Min Act: -0.0002

Data Index: 135115 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1056. Min Act: -0.0002

Data Index: 324652 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1072. Min Act: -0.0002

Data Index: 1522453 (Python Code)

Max Activating Token Index: 200

Text #5

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1607236 (Python Code)

Max Activating Token Index: 155

Text #6

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1038. Min Act: -0.0002

Data Index: 1298528 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1417351 (Python Code)

Max Activating Token Index: 87

Text #8

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0960. Min Act: -0.0002

Data Index: 1537214 (Python Code)

Max Activating Token Index: 723

Text #9

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1033. Min Act: -0.0002

Data Index: 303670 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1034. Min Act: -0.0002

Data Index: 686168 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0939. Min Act: -0.0002

Data Index: 1200093 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1649688 (Python Code)

Max Activating Token Index: 82

Text #13

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0991. Min Act: -0.0002

Data Index: 241008 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0959. Min Act: -0.0002

Data Index: 787893 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0973. Min Act: -0.0002

Data Index: 1315913 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0926. Min Act: -0.0002

Data Index: 1016032 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0963. Min Act: -0.0002

Data Index: 226384 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0905. Min Act: -0.0001

Data Index: 679918 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.0988. Min Act: -0.0002

Data Index: 1462753 (Python Code)

Max Activating Token Index: 483