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

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

Neuron 476 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: 5.0642. Min Range: -5.0642

Max Act: 5.0642. Min Act: -0.0000

Data Index: 651369 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 5.0642. Min Range: -5.0642

Max Act: 3.5840. Min Act: -0.0000

Data Index: 1165844 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 5.0642. Min Range: -5.0642

Max Act: 3.0833. Min Act: -0.0000

Data Index: 1023725 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 5.0642. Min Range: -5.0642

Max Act: 3.0566. Min Act: -0.0000

Data Index: 1339897 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 5.0642. Min Range: -5.0642

Max Act: 2.8476. Min Act: -0.0000

Data Index: 676808 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 5.0642. Min Range: -5.0642

Max Act: 2.7240. Min Act: -0.0000

Data Index: 783096 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 5.0642. Min Range: -5.0642

Max Act: 2.6789. Min Act: -0.0000

Data Index: 613550 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 5.0642. Min Range: -5.0642

Max Act: 2.9080. Min Act: -0.0000

Data Index: 381327 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 5.0642. Min Range: -5.0642

Max Act: 2.7434. Min Act: -0.0000

Data Index: 612039 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 5.0642. Min Range: -5.0642

Max Act: 2.3648. Min Act: -0.0000

Data Index: 1319578 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 5.0642. Min Range: -5.0642

Max Act: 2.6060. Min Act: -0.0000

Data Index: 86426 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 5.0642. Min Range: -5.0642

Max Act: 2.7112. Min Act: -0.0000

Data Index: 453735 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 5.0642. Min Range: -5.0642

Max Act: 2.8274. Min Act: -0.0000

Data Index: 218127 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 5.0642. Min Range: -5.0642

Max Act: 2.5713. Min Act: -0.0000

Data Index: 256498 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 5.0642. Min Range: -5.0642

Max Act: 2.5318. Min Act: -0.0000

Data Index: 355162 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 5.0642. Min Range: -5.0642

Max Act: 2.6218. Min Act: -0.0000

Data Index: 1018614 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 5.0642. Min Range: -5.0642

Max Act: 2.6221. Min Act: -0.0000

Data Index: 870781 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 5.0642. Min Range: -5.0642

Max Act: 2.7457. Min Act: -0.0000

Data Index: 989341 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 5.0642. Min Range: -5.0642

Max Act: 2.4580. Min Act: -0.0000

Data Index: 27871 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 5.0642. Min Range: -5.0642

Max Act: 2.5978. Min Act: -0.0000

Data Index: 1080153 (C4 (Web Text))

Max Activating Token Index: 1011