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

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

Neuron 534 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2267. Min Range: -6.2267

Max Act: 6.2267. Min Act: -0.0000

Data Index: 112724 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 6.2267. Min Range: -6.2267

Max Act: 5.8742. Min Act: -0.0000

Data Index: 398601 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 6.2267. Min Range: -6.2267

Max Act: 5.1309. Min Act: -0.0000

Data Index: 1137407 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 6.2267. Min Range: -6.2267

Max Act: 4.9355. Min Act: -0.0000

Data Index: 1116646 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 6.2267. Min Range: -6.2267

Max Act: 4.6262. Min Act: -0.0000

Data Index: 1230252 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 6.2267. Min Range: -6.2267

Max Act: 4.4389. Min Act: -0.0000

Data Index: 170640 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 6.2267. Min Range: -6.2267

Max Act: 4.7979. Min Act: -0.0000

Data Index: 597991 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 6.2267. Min Range: -6.2267

Max Act: 4.3768. Min Act: -0.0000

Data Index: 1168160 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 6.2267. Min Range: -6.2267

Max Act: 4.3991. Min Act: -0.0000

Data Index: 1144497 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 6.2267. Min Range: -6.2267

Max Act: 3.9820. Min Act: -0.0000

Data Index: 477609 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 6.2267. Min Range: -6.2267

Max Act: 4.0146. Min Act: -0.0000

Data Index: 932288 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 6.2267. Min Range: -6.2267

Max Act: 4.0841. Min Act: -0.0000

Data Index: 1077417 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 6.2267. Min Range: -6.2267

Max Act: 3.7788. Min Act: -0.0000

Data Index: 1300369 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 6.2267. Min Range: -6.2267

Max Act: 3.7397. Min Act: -0.0000

Data Index: 436907 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 6.2267. Min Range: -6.2267

Max Act: 3.6552. Min Act: -0.0000

Data Index: 1181291 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 6.2267. Min Range: -6.2267

Max Act: 3.6563. Min Act: -0.0000

Data Index: 621270 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 6.2267. Min Range: -6.2267

Max Act: 3.7366. Min Act: -0.0000

Data Index: 311700 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 6.2267. Min Range: -6.2267

Max Act: 3.5841. Min Act: -0.0000

Data Index: 748401 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 6.2267. Min Range: -6.2267

Max Act: 3.7069. Min Act: -0.0000

Data Index: 796589 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 6.2267. Min Range: -6.2267

Max Act: 3.2747. Min Act: -0.0000

Data Index: 276467 (C4 (Web Text))

Max Activating Token Index: 179