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

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

Neuron 384 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1727. Min Range: -3.1727

Max Act: 3.0358. Min Act: -0.0000

Data Index: 530544 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 3.1727. Min Range: -3.1727

Max Act: 3.0694. Min Act: -0.0000

Data Index: 532890 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 3.1727. Min Range: -3.1727

Max Act: 3.1727. Min Act: -0.0000

Data Index: 132153 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.9867. Min Act: -0.0000

Data Index: 307662 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 3.1727. Min Range: -3.1727

Max Act: 3.0889. Min Act: -0.0000

Data Index: 359119 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 3.1727. Min Range: -3.1727

Max Act: 3.0860. Min Act: -0.0000

Data Index: 1613935 (Python Code)

Max Activating Token Index: 223

Text #6

Max Range: 3.1727. Min Range: -3.1727

Max Act: 3.0048. Min Act: -0.0000

Data Index: 111863 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.9698. Min Act: -0.0000

Data Index: 1445515 (Python Code)

Max Activating Token Index: 96

Text #8

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.7616. Min Act: -0.0000

Data Index: 739894 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.7286. Min Act: -0.0000

Data Index: 1459705 (Python Code)

Max Activating Token Index: 525

Text #10

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.8389. Min Act: -0.0000

Data Index: 1618910 (Python Code)

Max Activating Token Index: 141

Text #11

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.7896. Min Act: -0.0000

Data Index: 139689 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.6486. Min Act: -0.0000

Data Index: 687086 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.7794. Min Act: -0.0000

Data Index: 470010 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.5035. Min Act: -0.0000

Data Index: 906665 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.5187. Min Act: -0.0000

Data Index: 1239876 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.4917. Min Act: -0.0000

Data Index: 128453 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.6264. Min Act: -0.0000

Data Index: 1462735 (Python Code)

Max Activating Token Index: 400

Text #18

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.3532. Min Act: -0.0000

Data Index: 650621 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.3444. Min Act: -0.0000

Data Index: 1464666 (Python Code)

Max Activating Token Index: 171