Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1509 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.7472. Min Act: -0.0000

Data Index: 91889 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6614. Min Act: -0.0000

Data Index: 574750 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1110393 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6276. Min Act: 0.0000

Data Index: 1129916 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1049560 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5605. Min Act: -0.0000

Data Index: 571327 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5815. Min Act: -0.0000

Data Index: 665811 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1196616 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5561. Min Act: 0.0000

Data Index: 371035 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5377. Min Act: -0.0000

Data Index: 147073 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5100. Min Act: -0.0000

Data Index: 685429 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5367. Min Act: -0.0001

Data Index: 1311915 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5098. Min Act: -0.0000

Data Index: 102316 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1179346 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5037. Min Act: -0.0000

Data Index: 409776 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4856. Min Act: 0.0000

Data Index: 812099 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4753. Min Act: -0.0000

Data Index: 846482 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1079260 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4746. Min Act: 0.0000

Data Index: 556781 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4579. Min Act: -0.0000

Data Index: 666774 (C4 (Web Text))

Max Activating Token Index: 813