Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3031 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0090. Min Act: -0.0003

Data Index: 1018571 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0088. Min Act: -0.0003

Data Index: 485602 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0087. Min Act: -0.0003

Data Index: 46483 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0087. Min Act: -0.0003

Data Index: 293623 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0087. Min Act: -0.0003

Data Index: 886720 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0085. Min Act: -0.0003

Data Index: 76095 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0084. Min Act: -0.0003

Data Index: 841490 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0085. Min Act: -0.0003

Data Index: 275779 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0084. Min Act: -0.0003

Data Index: 610993 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0003

Data Index: 799257 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1308131 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1052482 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0082. Min Act: -0.0003

Data Index: 218884 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0003

Data Index: 461140 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1220234 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0082. Min Act: -0.0003

Data Index: 208071 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0081. Min Act: -0.0003

Data Index: 455067 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0081. Min Act: -0.0003

Data Index: 341953 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1029266 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0081. Min Act: -0.0003

Data Index: 487786 (C4 (Web Text))

Max Activating Token Index: 652