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

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

Neuron 1599 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: 0.2667. Min Range: -0.2667

Max Act: 0.2614. Min Act: -0.0000

Data Index: 15397 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2667. Min Act: -0.0000

Data Index: 2069 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2639. Min Act: -0.0000

Data Index: 512286 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2508. Min Act: -0.0000

Data Index: 1351201 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2311. Min Act: -0.0000

Data Index: 1182226 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2134. Min Act: -0.0000

Data Index: 1246692 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1106294 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1090777 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2105. Min Act: -0.0000

Data Index: 300042 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2047. Min Act: -0.0001

Data Index: 1795 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2056. Min Act: -0.0000

Data Index: 804352 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2253. Min Act: -0.0000

Data Index: 486967 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1982. Min Act: -0.0000

Data Index: 763828 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1287061 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1971. Min Act: -0.0000

Data Index: 221115 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1032921 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1998. Min Act: -0.0000

Data Index: 1044052 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1999. Min Act: -0.0000

Data Index: 509629 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2065. Min Act: -0.0000

Data Index: 340433 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1967. Min Act: -0.0001

Data Index: 1156757 (C4 (Web Text))

Max Activating Token Index: 289