Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1263 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1083. Min Act: -0.0005

Data Index: 645119 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0998. Min Act: -0.0005

Data Index: 991944 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0894. Min Act: -0.0005

Data Index: 1104753 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0821. Min Act: -0.0005

Data Index: 131203 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0843. Min Act: -0.0005

Data Index: 954792 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0822. Min Act: -0.0005

Data Index: 399232 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0806. Min Act: -0.0005

Data Index: 748488 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0798. Min Act: -0.0005

Data Index: 554350 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0730. Min Act: -0.0005

Data Index: 809831 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0784. Min Act: -0.0005

Data Index: 78752 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0699. Min Act: -0.0005

Data Index: 665305 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0722. Min Act: -0.0005

Data Index: 624097 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0692. Min Act: -0.0005

Data Index: 1166851 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0692. Min Act: -0.0005

Data Index: 777584 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0726. Min Act: -0.0005

Data Index: 81624 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0714. Min Act: -0.0005

Data Index: 468597 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0710. Min Act: -0.0005

Data Index: 251071 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0722. Min Act: -0.0005

Data Index: 1266950 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0730. Min Act: -0.0005

Data Index: 421617 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0693. Min Act: -0.0005

Data Index: 563839 (C4 (Web Text))

Max Activating Token Index: 591