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

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

Neuron 2458 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: 0.2906. Min Range: -0.2906

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1400514 (Python Code)

Max Activating Token Index: 839

Text #1

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1645760 (Python Code)

Max Activating Token Index: 303

Text #2

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2880. Min Act: -0.0000

Data Index: 1449678 (Python Code)

Max Activating Token Index: 1011

Text #3

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1037615 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2660. Min Act: -0.0000

Data Index: 740423 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2722. Min Act: -0.0000

Data Index: 1559673 (Python Code)

Max Activating Token Index: 642

Text #6

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1655560 (Python Code)

Max Activating Token Index: 83

Text #7

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2439. Min Act: -0.0000

Data Index: 130701 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1547923 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1545672 (Python Code)

Max Activating Token Index: 599

Text #10

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1098667 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2188. Min Act: -0.0000

Data Index: 24208 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1373861 (Python Code)

Max Activating Token Index: 466

Text #13

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2246. Min Act: -0.0000

Data Index: 134064 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2321. Min Act: -0.0000

Data Index: 841794 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1618011 (Python Code)

Max Activating Token Index: 440

Text #16

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1378189 (Python Code)

Max Activating Token Index: 534

Text #17

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1601386 (Python Code)

Max Activating Token Index: 820

Text #18

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1463012 (Python Code)

Max Activating Token Index: 406

Text #19

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2133. Min Act: -0.0000

Data Index: 1584175 (Python Code)

Max Activating Token Index: 653