Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6087 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0807. Min Act: -0.0002

Data Index: 814023 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1140327 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0731. Min Act: -0.0002

Data Index: 744270 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0753. Min Act: -0.0002

Data Index: 678015 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0731. Min Act: -0.0002

Data Index: 970923 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0736. Min Act: -0.0002

Data Index: 438928 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1332013 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0713. Min Act: -0.0002

Data Index: 73479 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1150344 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1212063 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1002483 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0674. Min Act: -0.0002

Data Index: 906117 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0671. Min Act: -0.0002

Data Index: 679951 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0670. Min Act: -0.0002

Data Index: 767374 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0694. Min Act: -0.0002

Data Index: 415727 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0664. Min Act: -0.0002

Data Index: 187728 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0654. Min Act: -0.0002

Data Index: 321759 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1214379 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0655. Min Act: -0.0002

Data Index: 292990 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0654. Min Act: -0.0002

Data Index: 579592 (C4 (Web Text))

Max Activating Token Index: 763