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

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

Neuron 809 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: 1.7677. Min Range: -1.7677

Max Act: 1.7677. Min Act: -0.0000

Data Index: 1615969 (Python Code)

Max Activating Token Index: 49

Text #1

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.6157. Min Act: -0.0000

Data Index: 475403 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.5721. Min Act: -0.0000

Data Index: 1514627 (Python Code)

Max Activating Token Index: 144

Text #3

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.2608. Min Act: -0.0000

Data Index: 153833 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.4834. Min Act: -0.0000

Data Index: 1455923 (Python Code)

Max Activating Token Index: 819

Text #5

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.3019. Min Act: -0.0000

Data Index: 1403975 (Python Code)

Max Activating Token Index: 495

Text #6

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.2079. Min Act: -0.0000

Data Index: 1057895 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.2968. Min Act: -0.0000

Data Index: 1606344 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.0993. Min Act: -0.0000

Data Index: 1365772 (Python Code)

Max Activating Token Index: 858

Text #9

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.1476. Min Act: -0.0000

Data Index: 388756 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 1.7677. Min Range: -1.7677

Max Act: 0.9839. Min Act: -0.0000

Data Index: 1403986 (Python Code)

Max Activating Token Index: 812

Text #11

Max Range: 1.7677. Min Range: -1.7677

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1567283 (Python Code)

Max Activating Token Index: 170

Text #12

Max Range: 1.7677. Min Range: -1.7677

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1501167 (Python Code)

Max Activating Token Index: 473

Text #13

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.0171. Min Act: -0.0000

Data Index: 1492804 (Python Code)

Max Activating Token Index: 806

Text #14

Max Range: 1.7677. Min Range: -1.7677

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1628625 (Python Code)

Max Activating Token Index: 32

Text #15

Max Range: 1.7677. Min Range: -1.7677

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1631079 (Python Code)

Max Activating Token Index: 266

Text #16

Max Range: 1.7677. Min Range: -1.7677

Max Act: 0.9405. Min Act: -0.0000

Data Index: 129782 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 1.7677. Min Range: -1.7677

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1612788 (Python Code)

Max Activating Token Index: 320

Text #18

Max Range: 1.7677. Min Range: -1.7677

Max Act: 0.9733. Min Act: -0.0000

Data Index: 1464734 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 1.7677. Min Range: -1.7677

Max Act: 0.9538. Min Act: -0.0000

Data Index: 200752 (C4 (Web Text))

Max Activating Token Index: 234