Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3732 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6685. Min Act: -0.0001

Data Index: 1325797 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6275. Min Act: -0.0000

Data Index: 1010519 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6754. Min Act: -0.0000

Data Index: 774421 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6490. Min Act: -0.0001

Data Index: 33097 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6646. Min Act: -0.0000

Data Index: 824565 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6225. Min Act: -0.0001

Data Index: 857391 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6584. Min Act: -0.0000

Data Index: 610429 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6061. Min Act: -0.0001

Data Index: 1204983 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6338. Min Act: -0.0001

Data Index: 326470 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5885. Min Act: -0.0001

Data Index: 1258620 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6068. Min Act: -0.0001

Data Index: 83632 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1083276 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5608. Min Act: -0.0001

Data Index: 586588 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5785. Min Act: -0.0000

Data Index: 448949 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1304418 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5537. Min Act: -0.0001

Data Index: 1068287 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5516. Min Act: -0.0001

Data Index: 664157 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1111663 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.4947. Min Act: -0.0000

Data Index: 758906 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.4946. Min Act: -0.0000

Data Index: 879856 (C4 (Web Text))

Max Activating Token Index: 293