Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3960 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1365455 (Python Code)

Max Activating Token Index: 43

Text #1

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1389428 (Python Code)

Max Activating Token Index: 913

Text #2

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0107. Min Act: -0.0002

Data Index: 446987 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1122854 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0102. Min Act: -0.0002

Data Index: 1521173 (Python Code)

Max Activating Token Index: 63

Text #5

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0102. Min Act: -0.0002

Data Index: 738756 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0104. Min Act: -0.0002

Data Index: 709423 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0102. Min Act: -0.0002

Data Index: 1321560 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0100. Min Act: -0.0002

Data Index: 1493652 (Python Code)

Max Activating Token Index: 70

Text #9

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0099. Min Act: -0.0002

Data Index: 1468651 (Python Code)

Max Activating Token Index: 54

Text #10

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0099. Min Act: -0.0002

Data Index: 1620160 (Python Code)

Max Activating Token Index: 104

Text #11

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1050410 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0095. Min Act: -0.0002

Data Index: 1238581 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0091. Min Act: -0.0002

Data Index: 505055 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0093. Min Act: -0.0002

Data Index: 469539 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0092. Min Act: -0.0002

Data Index: 443588 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0091. Min Act: -0.0002

Data Index: 1606452 (Python Code)

Max Activating Token Index: 42

Text #17

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0089. Min Act: -0.0002

Data Index: 159399 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1569784 (Python Code)

Max Activating Token Index: 58

Text #19

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0088. Min Act: -0.0002

Data Index: 2416 (C4 (Web Text))

Max Activating Token Index: 48