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

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

Neuron 2709 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1219. Min Act: -0.0000

Data Index: 214479 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0960. Min Act: -0.0000

Data Index: 44297 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0882. Min Act: -0.0000

Data Index: 139438 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0888. Min Act: -0.0000

Data Index: 86690 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0837. Min Act: -0.0000

Data Index: 172118 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0826. Min Act: -0.0001

Data Index: 594559 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1005317 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0775. Min Act: -0.0001

Data Index: 1469862 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0729. Min Act: -0.0001

Data Index: 892229 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0796. Min Act: -0.0000

Data Index: 971187 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0711. Min Act: -0.0000

Data Index: 1034909 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0730. Min Act: -0.0000

Data Index: 1091447 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0736. Min Act: -0.0000

Data Index: 753729 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0736. Min Act: -0.0000

Data Index: 566404 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0735. Min Act: -0.0000

Data Index: 355400 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0736. Min Act: -0.0000

Data Index: 831615 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0710. Min Act: -0.0000

Data Index: 308353 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0727. Min Act: -0.0000

Data Index: 907333 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0754. Min Act: -0.0001

Data Index: 539765 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0700. Min Act: -0.0000

Data Index: 227264 (C4 (Web Text))

Max Activating Token Index: 1018