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

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

Neuron 1538 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.6952. Min Act: -0.0000

Data Index: 408204 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.6672. Min Act: -0.0000

Data Index: 935176 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.6109. Min Act: -0.0000

Data Index: 668668 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1132153 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5917. Min Act: -0.0000

Data Index: 656149 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1181014 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5879. Min Act: -0.0000

Data Index: 146480 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5688. Min Act: -0.0000

Data Index: 647903 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5634. Min Act: -0.0000

Data Index: 1248195 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5801. Min Act: -0.0000

Data Index: 840513 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5397. Min Act: -0.0000

Data Index: 303804 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5390. Min Act: -0.0000

Data Index: 507029 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1274999 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5190. Min Act: -0.0000

Data Index: 438730 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1047765 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5368. Min Act: -0.0000

Data Index: 33975 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5342. Min Act: -0.0000

Data Index: 752783 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5124. Min Act: -0.0000

Data Index: 208101 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5082. Min Act: -0.0000

Data Index: 341826 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.6952. Min Range: -0.6952

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1352587 (C4 (Web Text))

Max Activating Token Index: 213