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

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

Neuron 1247 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1253528 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1135153 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0767. Min Act: -0.0002

Data Index: 521865 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0784. Min Act: -0.0002

Data Index: 143266 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1127634 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0781. Min Act: -0.0001

Data Index: 626126 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1094488 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0751. Min Act: -0.0002

Data Index: 849178 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0710. Min Act: -0.0001

Data Index: 39643 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0738. Min Act: -0.0002

Data Index: 905672 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0725. Min Act: -0.0002

Data Index: 572223 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0754. Min Act: -0.0002

Data Index: 299915 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0721. Min Act: -0.0002

Data Index: 733579 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0715. Min Act: -0.0001

Data Index: 1164388 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0708. Min Act: -0.0002

Data Index: 183395 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0709. Min Act: -0.0001

Data Index: 962571 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0709. Min Act: -0.0002

Data Index: 689629 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0708. Min Act: -0.0001

Data Index: 611021 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0705. Min Act: -0.0002

Data Index: 371443 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0703. Min Act: -0.0002

Data Index: 479252 (C4 (Web Text))

Max Activating Token Index: 573