Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6053 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.7057. Min Range: -5.7057

Max Act: 5.7057. Min Act: 0.0001

Data Index: 1272783 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 5.7057. Min Range: -5.7057

Max Act: 4.6954. Min Act: 0.0000

Data Index: 129165 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 5.7057. Min Range: -5.7057

Max Act: 4.2042. Min Act: -0.0000

Data Index: 427642 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 5.7057. Min Range: -5.7057

Max Act: 4.2771. Min Act: -0.0000

Data Index: 56818 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 5.7057. Min Range: -5.7057

Max Act: 4.2655. Min Act: 0.0002

Data Index: 108391 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 5.7057. Min Range: -5.7057

Max Act: 4.2583. Min Act: -0.0000

Data Index: 10201 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 5.7057. Min Range: -5.7057

Max Act: 4.0724. Min Act: -0.0000

Data Index: 1096891 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 5.7057. Min Range: -5.7057

Max Act: 4.0306. Min Act: 0.0001

Data Index: 360632 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 5.7057. Min Range: -5.7057

Max Act: 4.0099. Min Act: -0.0000

Data Index: 454584 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 5.7057. Min Range: -5.7057

Max Act: 4.0519. Min Act: 0.0001

Data Index: 1059948 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 5.7057. Min Range: -5.7057

Max Act: 4.0266. Min Act: -0.0000

Data Index: 249693 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 5.7057. Min Range: -5.7057

Max Act: 4.0106. Min Act: -0.0000

Data Index: 24358 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 5.7057. Min Range: -5.7057

Max Act: 3.8043. Min Act: -0.0000

Data Index: 1043241 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 5.7057. Min Range: -5.7057

Max Act: 3.9848. Min Act: 0.0001

Data Index: 1298993 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 5.7057. Min Range: -5.7057

Max Act: 3.9473. Min Act: -0.0000

Data Index: 722014 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 5.7057. Min Range: -5.7057

Max Act: 3.9285. Min Act: -0.0000

Data Index: 965051 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 5.7057. Min Range: -5.7057

Max Act: 3.8859. Min Act: -0.0000

Data Index: 829371 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 5.7057. Min Range: -5.7057

Max Act: 3.8595. Min Act: -0.0000

Data Index: 1346016 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 5.7057. Min Range: -5.7057

Max Act: 3.6751. Min Act: -0.0000

Data Index: 830243 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 5.7057. Min Range: -5.7057

Max Act: 3.8164. Min Act: -0.0000

Data Index: 1094026 (C4 (Web Text))

Max Activating Token Index: 151