Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 739 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0102. Min Act: -0.0006

Data Index: 964397 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1277740 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0091. Min Act: -0.0005

Data Index: 1614489 (Python Code)

Max Activating Token Index: 354

Text #3

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0091. Min Act: -0.0006

Data Index: 1249683 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0091. Min Act: -0.0007

Data Index: 198957 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0088. Min Act: -0.0006

Data Index: 575285 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1330052 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0088. Min Act: -0.0006

Data Index: 901349 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0006

Data Index: 702510 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0086. Min Act: -0.0006

Data Index: 570988 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0086. Min Act: -0.0006

Data Index: 76921 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1011630 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1482360 (Python Code)

Max Activating Token Index: 999

Text #13

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1160987 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0084. Min Act: -0.0006

Data Index: 253326 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1001182 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0083. Min Act: -0.0006

Data Index: 613483 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0083. Min Act: -0.0006

Data Index: 207850 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0082. Min Act: -0.0005

Data Index: 1480714 (Python Code)

Max Activating Token Index: 312

Text #19

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0081. Min Act: -0.0005

Data Index: 1629321 (Python Code)

Max Activating Token Index: 260