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

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

Neuron 92 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1169. Min Act: -0.0002

Data Index: 1143743 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0935. Min Act: -0.0002

Data Index: 1180437 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0930. Min Act: -0.0002

Data Index: 956205 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0915. Min Act: -0.0002

Data Index: 696200 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1103104 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0897. Min Act: -0.0002

Data Index: 184847 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0838. Min Act: -0.0002

Data Index: 356354 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0833. Min Act: -0.0002

Data Index: 69612 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0776. Min Act: -0.0002

Data Index: 602076 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0834. Min Act: -0.0002

Data Index: 955308 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0741. Min Act: -0.0002

Data Index: 156850 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0728. Min Act: -0.0002

Data Index: 387786 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0796. Min Act: -0.0002

Data Index: 508036 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0664. Min Act: -0.0002

Data Index: 483885 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0794. Min Act: -0.0002

Data Index: 154177 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1104097 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0732. Min Act: -0.0002

Data Index: 884518 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0722. Min Act: -0.0002

Data Index: 888435 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1072454 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0644. Min Act: -0.0002

Data Index: 935943 (C4 (Web Text))

Max Activating Token Index: 720