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

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

Neuron 2887 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2393. Min Act: -0.0001

Data Index: 219208 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2454. Min Act: -0.0001

Data Index: 129299 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2212. Min Act: -0.0000

Data Index: 92602 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2297. Min Act: -0.0001

Data Index: 278898 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2284. Min Act: -0.0000

Data Index: 923944 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2127. Min Act: -0.0000

Data Index: 727678 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2192. Min Act: -0.0000

Data Index: 207620 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1294919 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2178. Min Act: -0.0000

Data Index: 952441 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1003934 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2217. Min Act: -0.0001

Data Index: 827870 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2116. Min Act: -0.0000

Data Index: 512679 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2029. Min Act: -0.0000

Data Index: 811517 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1939. Min Act: -0.0000

Data Index: 630102 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2061. Min Act: -0.0001

Data Index: 616864 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2007. Min Act: -0.0000

Data Index: 553098 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1082174 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1928. Min Act: -0.0001

Data Index: 1150175 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2070. Min Act: -0.0001

Data Index: 67088 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2059. Min Act: -0.0000

Data Index: 1208402 (C4 (Web Text))

Max Activating Token Index: 455