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

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

Neuron 4657 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.6639. Min Act: -0.0000

Data Index: 367081 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5363. Min Act: -0.0000

Data Index: 941467 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5449. Min Act: -0.0000

Data Index: 158880 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5660. Min Act: -0.0000

Data Index: 926548 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4900. Min Act: -0.0000

Data Index: 824666 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4624. Min Act: -0.0000

Data Index: 848767 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1024230 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5067. Min Act: -0.0000

Data Index: 823978 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4804. Min Act: -0.0000

Data Index: 554306 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4838. Min Act: -0.0000

Data Index: 762393 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5020. Min Act: -0.0000

Data Index: 515993 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4804. Min Act: -0.0000

Data Index: 522827 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4769. Min Act: -0.0000

Data Index: 734059 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4442. Min Act: -0.0000

Data Index: 181158 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4172. Min Act: -0.0000

Data Index: 787388 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4287. Min Act: -0.0000

Data Index: 508430 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4305. Min Act: -0.0000

Data Index: 519238 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1044335 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4107. Min Act: -0.0000

Data Index: 334680 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4344. Min Act: -0.0000

Data Index: 40682 (C4 (Web Text))

Max Activating Token Index: 946