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

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

Neuron 2034 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5095. Min Range: -1.5095

Max Act: 1.5095. Min Act: -0.0002

Data Index: 1190532 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 1.5095. Min Range: -1.5095

Max Act: 1.1587. Min Act: -0.0002

Data Index: 209365 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 1.5095. Min Range: -1.5095

Max Act: 1.0803. Min Act: -0.0002

Data Index: 207971 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 1.5095. Min Range: -1.5095

Max Act: 1.1862. Min Act: -0.0002

Data Index: 702775 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 1.5095. Min Range: -1.5095

Max Act: 1.1101. Min Act: -0.0002

Data Index: 676166 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 1.5095. Min Range: -1.5095

Max Act: 0.9883. Min Act: -0.0002

Data Index: 806063 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 1.5095. Min Range: -1.5095

Max Act: 1.0655. Min Act: -0.0002

Data Index: 1313401 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 1.5095. Min Range: -1.5095

Max Act: 1.0396. Min Act: -0.0002

Data Index: 272643 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 1.5095. Min Range: -1.5095

Max Act: 1.0686. Min Act: -0.0002

Data Index: 739477 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 1.5095. Min Range: -1.5095

Max Act: 1.0274. Min Act: -0.0002

Data Index: 1109355 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 1.5095. Min Range: -1.5095

Max Act: 0.9771. Min Act: -0.0002

Data Index: 46708 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 1.5095. Min Range: -1.5095

Max Act: 0.9406. Min Act: -0.0002

Data Index: 550358 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 1.5095. Min Range: -1.5095

Max Act: 0.9954. Min Act: -0.0002

Data Index: 1303689 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.5095. Min Range: -1.5095

Max Act: 1.0081. Min Act: -0.0002

Data Index: 236331 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 1.5095. Min Range: -1.5095

Max Act: 0.9889. Min Act: -0.0002

Data Index: 453233 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 1.5095. Min Range: -1.5095

Max Act: 0.9679. Min Act: -0.0002

Data Index: 403630 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 1.5095. Min Range: -1.5095

Max Act: 0.9109. Min Act: -0.0002

Data Index: 1140283 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 1.5095. Min Range: -1.5095

Max Act: 0.9289. Min Act: -0.0002

Data Index: 812493 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 1.5095. Min Range: -1.5095

Max Act: 0.9823. Min Act: -0.0002

Data Index: 1098749 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 1.5095. Min Range: -1.5095

Max Act: 0.9505. Min Act: -0.0002

Data Index: 927574 (C4 (Web Text))

Max Activating Token Index: 952