Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 743 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2429. Min Act: -0.0001

Data Index: 889436 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2468. Min Act: -0.0001

Data Index: 868040 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2394. Min Act: -0.0001

Data Index: 397035 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2298. Min Act: -0.0001

Data Index: 866432 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2368. Min Act: -0.0001

Data Index: 216693 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2262. Min Act: -0.0001

Data Index: 556074 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2403. Min Act: -0.0001

Data Index: 427313 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2257. Min Act: -0.0001

Data Index: 870695 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2016. Min Act: -0.0001

Data Index: 841921 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2046. Min Act: -0.0001

Data Index: 650644 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2111. Min Act: -0.0001

Data Index: 601001 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2079. Min Act: -0.0001

Data Index: 1044381 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1113814 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1976. Min Act: -0.0001

Data Index: 417445 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1886. Min Act: -0.0001

Data Index: 1277411 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1888. Min Act: -0.0001

Data Index: 2018 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2019. Min Act: -0.0001

Data Index: 1267940 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1860. Min Act: -0.0001

Data Index: 663765 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2002. Min Act: -0.0001

Data Index: 484336 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1843. Min Act: -0.0001

Data Index: 385667 (C4 (Web Text))

Max Activating Token Index: 942