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

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

Neuron 3922 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: 0.7051. Min Range: -0.7051

Max Act: 0.7051. Min Act: -0.0000

Data Index: 538209 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6570. Min Act: -0.0000

Data Index: 569012 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6527. Min Act: -0.0000

Data Index: 909785 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5693. Min Act: -0.0000

Data Index: 876521 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6040. Min Act: -0.0000

Data Index: 788222 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5549. Min Act: -0.0000

Data Index: 275156 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5949. Min Act: -0.0000

Data Index: 292343 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5610. Min Act: -0.0000

Data Index: 104346 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5469. Min Act: -0.0000

Data Index: 623589 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5413. Min Act: -0.0000

Data Index: 194773 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5208. Min Act: -0.0000

Data Index: 695591 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5174. Min Act: -0.0000

Data Index: 846716 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5321. Min Act: -0.0000

Data Index: 778335 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5281. Min Act: -0.0000

Data Index: 748315 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5110. Min Act: -0.0000

Data Index: 407622 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4947. Min Act: -0.0000

Data Index: 276105 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4926. Min Act: -0.0000

Data Index: 163147 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1204686 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1136088 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4687. Min Act: -0.0000

Data Index: 128474 (C4 (Web Text))

Max Activating Token Index: 977