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

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

Neuron 2675 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1108. Min Act: -0.0001

Data Index: 968063 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1068585 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0908. Min Act: -0.0000

Data Index: 649466 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1223018 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0945. Min Act: -0.0000

Data Index: 538559 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0913. Min Act: -0.0000

Data Index: 723076 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0861. Min Act: -0.0000

Data Index: 48640 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0850. Min Act: -0.0000

Data Index: 747596 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1008539 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0863. Min Act: -0.0000

Data Index: 402466 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0800. Min Act: -0.0000

Data Index: 923459 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0854. Min Act: -0.0000

Data Index: 159809 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0780. Min Act: -0.0001

Data Index: 961345 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0824. Min Act: -0.0000

Data Index: 45379 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0848. Min Act: -0.0000

Data Index: 630158 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0815. Min Act: -0.0000

Data Index: 824298 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0812. Min Act: -0.0000

Data Index: 916469 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0812. Min Act: -0.0000

Data Index: 477422 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1233746 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0720. Min Act: -0.0001

Data Index: 897785 (C4 (Web Text))

Max Activating Token Index: 696