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

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

Neuron 1436 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: 0.0212. Min Range: -0.0212

Max Act: 0.0212. Min Act: -0.0006

Data Index: 840601 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0102. Min Act: -0.0006

Data Index: 591607 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1326596 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0095. Min Act: -0.0005

Data Index: 1542653 (Python Code)

Max Activating Token Index: 533

Text #4

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1484211 (Python Code)

Max Activating Token Index: 880

Text #5

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1604480 (Python Code)

Max Activating Token Index: 856

Text #6

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0096. Min Act: -0.0006

Data Index: 334514 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1282763 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1452852 (Python Code)

Max Activating Token Index: 842

Text #9

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1578458 (Python Code)

Max Activating Token Index: 918

Text #10

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0094. Min Act: -0.0006

Data Index: 666193 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0097. Min Act: -0.0005

Data Index: 1447912 (Python Code)

Max Activating Token Index: 1021

Text #12

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1633051 (Python Code)

Max Activating Token Index: 923

Text #13

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0096. Min Act: -0.0005

Data Index: 1402381 (Python Code)

Max Activating Token Index: 864

Text #14

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0091. Min Act: -0.0006

Data Index: 32615 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0092. Min Act: -0.0005

Data Index: 1483839 (Python Code)

Max Activating Token Index: 855

Text #16

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0091. Min Act: -0.0005

Data Index: 1622912 (Python Code)

Max Activating Token Index: 959

Text #17

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0086. Min Act: -0.0006

Data Index: 641435 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1440270 (Python Code)

Max Activating Token Index: 541

Text #19

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0090. Min Act: -0.0006

Data Index: 752626 (C4 (Web Text))

Max Activating Token Index: 1023