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

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

Neuron 3433 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.6144. Min Act: -0.0000

Data Index: 308206 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5619. Min Act: -0.0000

Data Index: 273898 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4923. Min Act: -0.0000

Data Index: 828167 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5843. Min Act: -0.0000

Data Index: 409924 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5110. Min Act: -0.0000

Data Index: 186714 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5248. Min Act: -0.0000

Data Index: 82579 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5251. Min Act: -0.0000

Data Index: 361075 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5021. Min Act: -0.0000

Data Index: 151465 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4907. Min Act: -0.0000

Data Index: 559850 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4891. Min Act: -0.0000

Data Index: 614522 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1187113 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4545. Min Act: -0.0000

Data Index: 2238 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4615. Min Act: -0.0000

Data Index: 443442 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4782. Min Act: -0.0000

Data Index: 89134 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4815. Min Act: -0.0000

Data Index: 1080648 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4596. Min Act: -0.0000

Data Index: 215387 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1136239 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1282558 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4418. Min Act: -0.0000

Data Index: 596692 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4364. Min Act: -0.0000

Data Index: 403970 (C4 (Web Text))

Max Activating Token Index: 691