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

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

Neuron 526 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.4233. Min Act: -0.0003

Data Index: 753400 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.4068. Min Act: -0.0002

Data Index: 391426 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3975. Min Act: -0.0002

Data Index: 724020 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3912. Min Act: -0.0003

Data Index: 1111241 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3887. Min Act: -0.0003

Data Index: 550965 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3727. Min Act: -0.0002

Data Index: 165515 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3726. Min Act: -0.0002

Data Index: 560982 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3937. Min Act: -0.0002

Data Index: 1097983 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3551. Min Act: -0.0002

Data Index: 322032 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3930. Min Act: -0.0002

Data Index: 230738 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3791. Min Act: -0.0002

Data Index: 310193 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3748. Min Act: -0.0002

Data Index: 160010 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3745. Min Act: -0.0002

Data Index: 1184196 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3729. Min Act: -0.0003

Data Index: 571593 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3491. Min Act: -0.0003

Data Index: 39597 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3523. Min Act: -0.0002

Data Index: 1271265 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3662. Min Act: -0.0002

Data Index: 1019692 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3490. Min Act: -0.0002

Data Index: 1126061 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3701. Min Act: -0.0002

Data Index: 1139922 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3596. Min Act: -0.0002

Data Index: 1101137 (C4 (Web Text))

Max Activating Token Index: 943