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

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

Neuron 4387 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: 0.0096. Min Range: -0.0096

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1275147 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0096. Min Act: -0.0002

Data Index: 710478 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0096. Min Act: -0.0002

Data Index: 133450 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0094. Min Act: -0.0002

Data Index: 900650 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1031743 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0094. Min Act: -0.0002

Data Index: 291077 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0093. Min Act: -0.0002

Data Index: 639190 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0093. Min Act: -0.0002

Data Index: 811410 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0094. Min Act: -0.0002

Data Index: 449691 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0091. Min Act: -0.0002

Data Index: 613357 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0092. Min Act: -0.0002

Data Index: 577497 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1044182 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0090. Min Act: -0.0002

Data Index: 596011 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1154415 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0092. Min Act: -0.0002

Data Index: 176969 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0090. Min Act: -0.0002

Data Index: 353598 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1291215 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0089. Min Act: -0.0002

Data Index: 924125 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1165971 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0089. Min Act: -0.0002

Data Index: 38063 (C4 (Web Text))

Max Activating Token Index: 5