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

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

Neuron 3980 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: 0.3564. Min Range: -0.3564

Max Act: 0.3564. Min Act: -0.0000

Data Index: 722627 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.3141. Min Act: -0.0000

Data Index: 827555 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2475. Min Act: -0.0000

Data Index: 395806 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2350. Min Act: -0.0000

Data Index: 973316 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2291. Min Act: -0.0000

Data Index: 394352 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2209. Min Act: -0.0000

Data Index: 128505 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1583611 (Python Code)

Max Activating Token Index: 992

Text #7

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1650634 (Python Code)

Max Activating Token Index: 886

Text #8

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2474. Min Act: -0.0000

Data Index: 303915 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1054880 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1150608 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2101. Min Act: -0.0000

Data Index: 248988 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1553462 (Python Code)

Max Activating Token Index: 643

Text #13

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2052. Min Act: -0.0000

Data Index: 450219 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1221733 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1372415 (Python Code)

Max Activating Token Index: 625

Text #16

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.1829. Min Act: -0.0000

Data Index: 290629 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1495663 (Python Code)

Max Activating Token Index: 580

Text #18

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1310462 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.3564. Min Range: -0.3564

Max Act: 0.1881. Min Act: -0.0000

Data Index: 1378223 (Python Code)

Max Activating Token Index: 850