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

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

Neuron 4968 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: 0.8981. Min Range: -0.8981

Max Act: 0.8549. Min Act: -0.0000

Data Index: 491090 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8981. Min Act: -0.0000

Data Index: 387952 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8356. Min Act: -0.0000

Data Index: 468816 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8050. Min Act: -0.0000

Data Index: 906525 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8350. Min Act: -0.0000

Data Index: 124471 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8365. Min Act: -0.0000

Data Index: 982694 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7585. Min Act: -0.0000

Data Index: 10259 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1162030 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8180. Min Act: -0.0000

Data Index: 656991 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1269313 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7602. Min Act: -0.0000

Data Index: 168101 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7324. Min Act: -0.0000

Data Index: 494698 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7505. Min Act: -0.0000

Data Index: 687959 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7221. Min Act: -0.0000

Data Index: 934864 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1070668 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7215. Min Act: -0.0000

Data Index: 1328530 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1075567 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7002. Min Act: -0.0000

Data Index: 757569 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1018329 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1047026 (C4 (Web Text))

Max Activating Token Index: 319