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

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

Neuron 4544 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: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0001

Data Index: 1413790 (Python Code)

Max Activating Token Index: 298

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0130. Min Act: -0.0002

Data Index: 412694 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1150444 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0098. Min Act: -0.0002

Data Index: 613055 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0095. Min Act: -0.0002

Data Index: 780380 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0083. Min Act: -0.0002

Data Index: 36539 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0082. Min Act: -0.0002

Data Index: 1005426 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0082. Min Act: -0.0002

Data Index: 1039333 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0081. Min Act: -0.0002

Data Index: 178691 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0079. Min Act: -0.0002

Data Index: 240044 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1425742 (Python Code)

Max Activating Token Index: 65

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0078. Min Act: -0.0002

Data Index: 467173 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0076. Min Act: -0.0002

Data Index: 206029 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0076. Min Act: -0.0002

Data Index: 606189 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0075. Min Act: -0.0002

Data Index: 825295 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0075. Min Act: -0.0002

Data Index: 1560997 (Python Code)

Max Activating Token Index: 898

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0075. Min Act: -0.0002

Data Index: 551878 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0074. Min Act: -0.0002

Data Index: 334792 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0074. Min Act: -0.0002

Data Index: 397243 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0073. Min Act: -0.0002

Data Index: 1572168 (Python Code)

Max Activating Token Index: 494