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

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

Neuron 1215 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0327. Min Range: -1.0327

Max Act: 1.0327. Min Act: -0.0000

Data Index: 26522 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8916. Min Act: -0.0000

Data Index: 107118 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.9910. Min Act: -0.0000

Data Index: 932481 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.9956. Min Act: -0.0000

Data Index: 214886 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.9844. Min Act: -0.0000

Data Index: 548142 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8858. Min Act: -0.0000

Data Index: 706315 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.9092. Min Act: -0.0000

Data Index: 736906 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.9311. Min Act: -0.0000

Data Index: 1098517 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.9219. Min Act: -0.0000

Data Index: 1022783 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8386. Min Act: -0.0001

Data Index: 556751 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8548. Min Act: -0.0000

Data Index: 791167 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.9348. Min Act: -0.0000

Data Index: 370269 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8729. Min Act: -0.0000

Data Index: 498359 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8766. Min Act: -0.0000

Data Index: 291013 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8668. Min Act: -0.0000

Data Index: 488523 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8118. Min Act: -0.0000

Data Index: 9773 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8369. Min Act: -0.0000

Data Index: 910645 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8577. Min Act: -0.0000

Data Index: 1244101 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1150114 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8517. Min Act: -0.0000

Data Index: 218065 (C4 (Web Text))

Max Activating Token Index: 27