Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 157 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0074. Min Act: -0.0003

Data Index: 1546781 (Python Code)

Max Activating Token Index: 828

Text #1

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0044. Min Act: -0.0004

Data Index: 1304110 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0048. Min Act: -0.0004

Data Index: 710362 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0042. Min Act: -0.0004

Data Index: 1503105 (Python Code)

Max Activating Token Index: 216

Text #4

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0045. Min Act: -0.0003

Data Index: 66691 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0044. Min Act: -0.0004

Data Index: 646388 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0045. Min Act: -0.0004

Data Index: 86101 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0047. Min Act: -0.0004

Data Index: 603496 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0041. Min Act: -0.0003

Data Index: 1110850 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0044. Min Act: -0.0004

Data Index: 1384837 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0043. Min Act: -0.0004

Data Index: 957996 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0041. Min Act: -0.0004

Data Index: 1373816 (Python Code)

Max Activating Token Index: 587

Text #12

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0042. Min Act: -0.0004

Data Index: 1571185 (Python Code)

Max Activating Token Index: 634

Text #13

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0042. Min Act: -0.0004

Data Index: 1111886 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0042. Min Act: -0.0004

Data Index: 100228 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0039. Min Act: -0.0004

Data Index: 1118084 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0041. Min Act: -0.0004

Data Index: 1441802 (Python Code)

Max Activating Token Index: 719

Text #17

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0041. Min Act: -0.0004

Data Index: 668234 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0041. Min Act: -0.0004

Data Index: 1265439 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0038. Min Act: -0.0004

Data Index: 655780 (C4 (Web Text))

Max Activating Token Index: 313