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

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

Neuron 3415 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4652. Min Range: -2.4652

Max Act: 2.4652. Min Act: -0.0000

Data Index: 279073 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 2.4652. Min Range: -2.4652

Max Act: 2.4112. Min Act: -0.0000

Data Index: 1345776 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 2.4652. Min Range: -2.4652

Max Act: 2.2812. Min Act: -0.0000

Data Index: 1050104 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 2.4652. Min Range: -2.4652

Max Act: 2.0923. Min Act: -0.0000

Data Index: 616955 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 2.4652. Min Range: -2.4652

Max Act: 2.3234. Min Act: -0.0000

Data Index: 233779 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 2.4652. Min Range: -2.4652

Max Act: 2.2147. Min Act: -0.0000

Data Index: 361343 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 2.4652. Min Range: -2.4652

Max Act: 1.8811. Min Act: -0.0000

Data Index: 580637 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 2.4652. Min Range: -2.4652

Max Act: 1.7800. Min Act: -0.0000

Data Index: 785204 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 2.4652. Min Range: -2.4652

Max Act: 1.9602. Min Act: -0.0000

Data Index: 61412 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 2.4652. Min Range: -2.4652

Max Act: 1.8133. Min Act: -0.0000

Data Index: 812078 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 2.4652. Min Range: -2.4652

Max Act: 1.6341. Min Act: -0.0000

Data Index: 637041 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 2.4652. Min Range: -2.4652

Max Act: 1.5941. Min Act: -0.0000

Data Index: 203774 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 2.4652. Min Range: -2.4652

Max Act: 1.8367. Min Act: -0.0000

Data Index: 733046 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 2.4652. Min Range: -2.4652

Max Act: 1.8206. Min Act: -0.0000

Data Index: 722563 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 2.4652. Min Range: -2.4652

Max Act: 1.5423. Min Act: -0.0000

Data Index: 59739 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 2.4652. Min Range: -2.4652

Max Act: 1.6793. Min Act: -0.0000

Data Index: 744871 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 2.4652. Min Range: -2.4652

Max Act: 1.5702. Min Act: -0.0000

Data Index: 650070 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 2.4652. Min Range: -2.4652

Max Act: 1.5891. Min Act: -0.0000

Data Index: 325105 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 2.4652. Min Range: -2.4652

Max Act: 1.3380. Min Act: -0.0000

Data Index: 470232 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 2.4652. Min Range: -2.4652

Max Act: 1.5882. Min Act: -0.0000

Data Index: 1017061 (C4 (Web Text))

Max Activating Token Index: 386