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

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

Neuron 1042 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1213. Min Act: -0.0000

Data Index: 126782 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1077. Min Act: -0.0000

Data Index: 542187 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0958. Min Act: -0.0000

Data Index: 464145 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0924. Min Act: -0.0000

Data Index: 699758 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1269395 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0899. Min Act: -0.0000

Data Index: 1344304 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1007626 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1492492 (Python Code)

Max Activating Token Index: 996

Text #8

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0871. Min Act: -0.0000

Data Index: 656357 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1305757 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0894. Min Act: -0.0000

Data Index: 561631 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0886. Min Act: -0.0000

Data Index: 615579 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1151910 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1619522 (Python Code)

Max Activating Token Index: 994

Text #14

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1641333 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0880. Min Act: -0.0000

Data Index: 310054 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0851. Min Act: -0.0000

Data Index: 411810 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0865. Min Act: -0.0000

Data Index: 1235519 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0864. Min Act: -0.0000

Data Index: 155726 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0821. Min Act: -0.0000

Data Index: 264442 (C4 (Web Text))

Max Activating Token Index: 289