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

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

Neuron 2292 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5016. Min Range: -3.5016

Max Act: 3.5016. Min Act: 0.0000

Data Index: 1522152 (Python Code)

Max Activating Token Index: 61

Text #1

Max Range: 3.5016. Min Range: -3.5016

Max Act: 3.1744. Min Act: 0.0000

Data Index: 1634774 (Python Code)

Max Activating Token Index: 129

Text #2

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.9029. Min Act: -0.0000

Data Index: 1447561 (Python Code)

Max Activating Token Index: 882

Text #3

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.8543. Min Act: -0.0000

Data Index: 1602654 (Python Code)

Max Activating Token Index: 114

Text #4

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.5830. Min Act: -0.0000

Data Index: 1393571 (Python Code)

Max Activating Token Index: 827

Text #5

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.5708. Min Act: -0.0000

Data Index: 1422073 (Python Code)

Max Activating Token Index: 918

Text #6

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.5715. Min Act: -0.0000

Data Index: 1406169 (Python Code)

Max Activating Token Index: 227

Text #7

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.5151. Min Act: -0.0000

Data Index: 608472 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.4584. Min Act: -0.0000

Data Index: 1391326 (Python Code)

Max Activating Token Index: 497

Text #9

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.5794. Min Act: -0.0000

Data Index: 75388 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.4714. Min Act: -0.0000

Data Index: 1617580 (Python Code)

Max Activating Token Index: 776

Text #11

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.5601. Min Act: -0.0000

Data Index: 1640942 (Python Code)

Max Activating Token Index: 78

Text #12

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.3309. Min Act: -0.0000

Data Index: 1607903 (Python Code)

Max Activating Token Index: 161

Text #13

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.3948. Min Act: 0.0001

Data Index: 1413613 (Python Code)

Max Activating Token Index: 138

Text #14

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.3425. Min Act: -0.0000

Data Index: 749927 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.2080. Min Act: -0.0000

Data Index: 1389794 (Python Code)

Max Activating Token Index: 836

Text #16

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.3481. Min Act: -0.0000

Data Index: 1597853 (Python Code)

Max Activating Token Index: 713

Text #17

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.3221. Min Act: -0.0000

Data Index: 1441790 (Python Code)

Max Activating Token Index: 609

Text #18

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.1430. Min Act: -0.0000

Data Index: 1390322 (Python Code)

Max Activating Token Index: 758

Text #19

Max Range: 3.5016. Min Range: -3.5016

Max Act: 2.0492. Min Act: -0.0000

Data Index: 1529450 (Python Code)

Max Activating Token Index: 740