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

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

Neuron 1992 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.0777. Min Act: -0.0000

Data Index: 1199948 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.2892. Min Act: -0.0000

Data Index: 635592 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.8693. Min Act: -0.0000

Data Index: 256808 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.8790. Min Act: -0.0000

Data Index: 1061125 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.8418. Min Act: -0.0000

Data Index: 135286 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.8210. Min Act: -0.0000

Data Index: 285803 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.8148. Min Act: -0.0000

Data Index: 22039 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.9709. Min Act: -0.0000

Data Index: 863454 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.7482. Min Act: -0.0000

Data Index: 155331 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.7238. Min Act: -0.0000

Data Index: 283252 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.7411. Min Act: -0.0000

Data Index: 726763 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.8100. Min Act: -0.0000

Data Index: 355708 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.8242. Min Act: -0.0000

Data Index: 8688 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.7880. Min Act: -0.0000

Data Index: 421272 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.6787. Min Act: -0.0000

Data Index: 299840 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.6178. Min Act: -0.0000

Data Index: 413073 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.5181. Min Act: -0.0000

Data Index: 1108621 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.4915. Min Act: -0.0000

Data Index: 709202 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.5879. Min Act: -0.0000

Data Index: 123870 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 2.2892. Min Range: -2.2892

Max Act: 1.5639. Min Act: -0.0000

Data Index: 191854 (C4 (Web Text))

Max Activating Token Index: 682