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

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

Neuron 1905 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5049. Min Range: -2.5049

Max Act: 2.3960. Min Act: -0.0000

Data Index: 731690 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 2.5049. Min Range: -2.5049

Max Act: 2.3670. Min Act: -0.0000

Data Index: 633876 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 2.5049. Min Range: -2.5049

Max Act: 2.1815. Min Act: -0.0000

Data Index: 1600609 (Python Code)

Max Activating Token Index: 1014

Text #3

Max Range: 2.5049. Min Range: -2.5049

Max Act: 2.5049. Min Act: -0.0000

Data Index: 1401963 (Python Code)

Max Activating Token Index: 894

Text #4

Max Range: 2.5049. Min Range: -2.5049

Max Act: 2.3806. Min Act: -0.0000

Data Index: 1436699 (Python Code)

Max Activating Token Index: 1014

Text #5

Max Range: 2.5049. Min Range: -2.5049

Max Act: 2.2321. Min Act: -0.0000

Data Index: 1537641 (Python Code)

Max Activating Token Index: 851

Text #6

Max Range: 2.5049. Min Range: -2.5049

Max Act: 2.1765. Min Act: -0.0000

Data Index: 1417396 (Python Code)

Max Activating Token Index: 842

Text #7

Max Range: 2.5049. Min Range: -2.5049

Max Act: 2.2739. Min Act: -0.0000

Data Index: 1642781 (Python Code)

Max Activating Token Index: 734

Text #8

Max Range: 2.5049. Min Range: -2.5049

Max Act: 2.1729. Min Act: -0.0000

Data Index: 1539233 (Python Code)

Max Activating Token Index: 621

Text #9

Max Range: 2.5049. Min Range: -2.5049

Max Act: 2.1600. Min Act: -0.0000

Data Index: 1624296 (Python Code)

Max Activating Token Index: 710

Text #10

Max Range: 2.5049. Min Range: -2.5049

Max Act: 1.9177. Min Act: -0.0000

Data Index: 1282780 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 2.5049. Min Range: -2.5049

Max Act: 2.0694. Min Act: -0.0000

Data Index: 253020 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 2.5049. Min Range: -2.5049

Max Act: 2.0378. Min Act: -0.0000

Data Index: 1480271 (Python Code)

Max Activating Token Index: 70

Text #13

Max Range: 2.5049. Min Range: -2.5049

Max Act: 1.8767. Min Act: -0.0000

Data Index: 1503648 (Python Code)

Max Activating Token Index: 222

Text #14

Max Range: 2.5049. Min Range: -2.5049

Max Act: 1.9574. Min Act: -0.0000

Data Index: 1417976 (Python Code)

Max Activating Token Index: 454

Text #15

Max Range: 2.5049. Min Range: -2.5049

Max Act: 1.9704. Min Act: -0.0000

Data Index: 1549230 (Python Code)

Max Activating Token Index: 276

Text #16

Max Range: 2.5049. Min Range: -2.5049

Max Act: 1.9217. Min Act: -0.0000

Data Index: 1451863 (Python Code)

Max Activating Token Index: 155

Text #17

Max Range: 2.5049. Min Range: -2.5049

Max Act: 1.9082. Min Act: -0.0000

Data Index: 1572818 (Python Code)

Max Activating Token Index: 148

Text #18

Max Range: 2.5049. Min Range: -2.5049

Max Act: 1.8281. Min Act: -0.0000

Data Index: 279850 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 2.5049. Min Range: -2.5049

Max Act: 1.7253. Min Act: -0.0000

Data Index: 526760 (C4 (Web Text))

Max Activating Token Index: 25