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

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

Neuron 4517 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9769. Min Range: -4.9769

Max Act: 4.9769. Min Act: -0.0000

Data Index: 1066192 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 4.9769. Min Range: -4.9769

Max Act: 4.5104. Min Act: -0.0000

Data Index: 1311236 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 4.9769. Min Range: -4.9769

Max Act: 4.5097. Min Act: -0.0000

Data Index: 507550 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 4.9769. Min Range: -4.9769

Max Act: 4.4621. Min Act: -0.0000

Data Index: 913555 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 4.9769. Min Range: -4.9769

Max Act: 4.1983. Min Act: -0.0000

Data Index: 129124 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 4.9769. Min Range: -4.9769

Max Act: 4.0225. Min Act: -0.0000

Data Index: 1249895 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 4.9769. Min Range: -4.9769

Max Act: 3.8662. Min Act: -0.0000

Data Index: 1188466 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 4.9769. Min Range: -4.9769

Max Act: 3.8704. Min Act: -0.0000

Data Index: 1029499 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 4.9769. Min Range: -4.9769

Max Act: 3.9711. Min Act: -0.0000

Data Index: 1302013 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 4.9769. Min Range: -4.9769

Max Act: 3.9487. Min Act: -0.0000

Data Index: 1254454 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 4.9769. Min Range: -4.9769

Max Act: 3.9262. Min Act: -0.0000

Data Index: 1048636 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 4.9769. Min Range: -4.9769

Max Act: 3.7572. Min Act: -0.0000

Data Index: 789070 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 4.9769. Min Range: -4.9769

Max Act: 3.5733. Min Act: -0.0000

Data Index: 1086235 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 4.9769. Min Range: -4.9769

Max Act: 3.5414. Min Act: -0.0000

Data Index: 180886 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 4.9769. Min Range: -4.9769

Max Act: 4.0115. Min Act: -0.0000

Data Index: 570312 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 4.9769. Min Range: -4.9769

Max Act: 3.5190. Min Act: -0.0000

Data Index: 1052382 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 4.9769. Min Range: -4.9769

Max Act: 3.6722. Min Act: -0.0000

Data Index: 91779 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 4.9769. Min Range: -4.9769

Max Act: 3.2976. Min Act: -0.0000

Data Index: 714173 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 4.9769. Min Range: -4.9769

Max Act: 3.5757. Min Act: -0.0000

Data Index: 346384 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 4.9769. Min Range: -4.9769

Max Act: 3.6451. Min Act: -0.0000

Data Index: 910878 (C4 (Web Text))

Max Activating Token Index: 348