Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2684 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.1695. Min Act: -0.0000

Data Index: 576315 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.8640. Min Act: -0.0000

Data Index: 48585 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.7970. Min Act: -0.0000

Data Index: 618230 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1359066 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1324259 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.7305. Min Act: -0.0000

Data Index: 278086 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.7283. Min Act: -0.0000

Data Index: 543617 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1176812 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.7241. Min Act: -0.0000

Data Index: 713855 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.7011. Min Act: -0.0000

Data Index: 590288 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1284222 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.6909. Min Act: -0.0000

Data Index: 844231 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1110001 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1203622 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.6733. Min Act: -0.0000

Data Index: 401258 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.6237. Min Act: -0.0000

Data Index: 346615 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.7201. Min Act: -0.0000

Data Index: 252996 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.6595. Min Act: -0.0000

Data Index: 265176 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.6796. Min Act: 0.0000

Data Index: 1322121 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.6117. Min Act: -0.0000

Data Index: 316796 (C4 (Web Text))

Max Activating Token Index: 956