Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 375 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0828. Min Act: -0.0002

Data Index: 776897 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0931. Min Act: -0.0001

Data Index: 979683 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0844. Min Act: -0.0002

Data Index: 835216 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0873. Min Act: -0.0002

Data Index: 1111609 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0722. Min Act: -0.0002

Data Index: 320914 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0728. Min Act: -0.0002

Data Index: 889521 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0771. Min Act: -0.0001

Data Index: 695794 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0664. Min Act: -0.0002

Data Index: 152513 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1053759 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0715. Min Act: -0.0001

Data Index: 239083 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0734. Min Act: -0.0001

Data Index: 912311 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0725. Min Act: -0.0002

Data Index: 587848 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0721. Min Act: -0.0002

Data Index: 776900 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0728. Min Act: -0.0001

Data Index: 40908 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1295668 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1040615 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0695. Min Act: -0.0001

Data Index: 355273 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0716. Min Act: -0.0002

Data Index: 415520 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1045725 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1156976 (C4 (Web Text))

Max Activating Token Index: 974