Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3935 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2006. Min Range: -3.2006

Max Act: 3.2006. Min Act: -0.0000

Data Index: 1655661 (Python Code)

Max Activating Token Index: 515

Text #1

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.9079. Min Act: -0.0000

Data Index: 1461179 (Python Code)

Max Activating Token Index: 262

Text #2

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.6057. Min Act: -0.0000

Data Index: 1485951 (Python Code)

Max Activating Token Index: 634

Text #3

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.5802. Min Act: -0.0000

Data Index: 1530107 (Python Code)

Max Activating Token Index: 990

Text #4

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.3814. Min Act: -0.0000

Data Index: 1530295 (Python Code)

Max Activating Token Index: 151

Text #5

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.4960. Min Act: -0.0000

Data Index: 1424719 (Python Code)

Max Activating Token Index: 744

Text #6

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.4437. Min Act: -0.0000

Data Index: 1451700 (Python Code)

Max Activating Token Index: 261

Text #7

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.4239. Min Act: -0.0000

Data Index: 1655657 (Python Code)

Max Activating Token Index: 851

Text #8

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.3808. Min Act: -0.0000

Data Index: 1656279 (Python Code)

Max Activating Token Index: 901

Text #9

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.3750. Min Act: -0.0000

Data Index: 1387617 (Python Code)

Max Activating Token Index: 716

Text #10

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.4343. Min Act: -0.0000

Data Index: 1552881 (Python Code)

Max Activating Token Index: 752

Text #11

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.5169. Min Act: -0.0000

Data Index: 1539465 (Python Code)

Max Activating Token Index: 887

Text #12

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.4018. Min Act: -0.0000

Data Index: 1628153 (Python Code)

Max Activating Token Index: 829

Text #13

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.3812. Min Act: -0.0000

Data Index: 1363765 (Python Code)

Max Activating Token Index: 422

Text #14

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.2716. Min Act: -0.0000

Data Index: 1600150 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.1410. Min Act: -0.0000

Data Index: 1603300 (Python Code)

Max Activating Token Index: 470

Text #16

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.3244. Min Act: -0.0000

Data Index: 1636460 (Python Code)

Max Activating Token Index: 716

Text #17

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.1794. Min Act: -0.0000

Data Index: 641405 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.2999. Min Act: -0.0000

Data Index: 1651110 (Python Code)

Max Activating Token Index: 315

Text #19

Max Range: 3.2006. Min Range: -3.2006

Max Act: 1.9226. Min Act: -0.0000

Data Index: 1434854 (Python Code)

Max Activating Token Index: 679