Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2782 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.2196. Min Act: -0.0001

Data Index: 1151567 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.2142. Min Act: -0.0001

Data Index: 643288 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.2023. Min Act: -0.0000

Data Index: 54484 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1979. Min Act: -0.0000

Data Index: 1111492 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1127271 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1998. Min Act: -0.0000

Data Index: 787095 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1921. Min Act: -0.0001

Data Index: 18530 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.2042. Min Act: -0.0001

Data Index: 656862 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1871. Min Act: -0.0001

Data Index: 634457 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1862. Min Act: -0.0001

Data Index: 1168206 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1874. Min Act: -0.0000

Data Index: 506805 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1837. Min Act: -0.0001

Data Index: 836863 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1822. Min Act: -0.0000

Data Index: 652437 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1804. Min Act: -0.0000

Data Index: 714421 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1786. Min Act: -0.0000

Data Index: 196441 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1782. Min Act: -0.0000

Data Index: 170191 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1716. Min Act: -0.0001

Data Index: 114354 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1653. Min Act: -0.0001

Data Index: 65301 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1757. Min Act: -0.0001

Data Index: 70136 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1035322 (C4 (Web Text))

Max Activating Token Index: 42