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

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

Neuron 3605 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0120. Min Act: -0.0003

Data Index: 825123 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0113. Min Act: -0.0002

Data Index: 694497 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0104. Min Act: -0.0003

Data Index: 467984 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1477611 (Python Code)

Max Activating Token Index: 21

Text #4

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1183563 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0108. Min Act: -0.0002

Data Index: 943871 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0104. Min Act: -0.0003

Data Index: 1217237 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0101. Min Act: -0.0003

Data Index: 1603733 (Python Code)

Max Activating Token Index: 23

Text #8

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0099. Min Act: -0.0002

Data Index: 745586 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0102. Min Act: -0.0002

Data Index: 1193834 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0100. Min Act: -0.0002

Data Index: 1297506 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0100. Min Act: -0.0003

Data Index: 47104 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0101. Min Act: -0.0003

Data Index: 610412 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0096. Min Act: -0.0002

Data Index: 989476 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0098. Min Act: -0.0003

Data Index: 1544160 (Python Code)

Max Activating Token Index: 21

Text #15

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1619170 (Python Code)

Max Activating Token Index: 113

Text #16

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1641811 (Python Code)

Max Activating Token Index: 12

Text #17

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0095. Min Act: -0.0003

Data Index: 1614629 (Python Code)

Max Activating Token Index: 87

Text #18

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1646724 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1464218 (Python Code)

Max Activating Token Index: 59