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

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

Neuron 2300 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.9291. Min Act: -0.0000

Data Index: 364273 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.8367. Min Act: -0.0000

Data Index: 1507522 (Python Code)

Max Activating Token Index: 213

Text #2

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.6609. Min Act: -0.0000

Data Index: 352392 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.7719. Min Act: -0.0000

Data Index: 1527280 (Python Code)

Max Activating Token Index: 983

Text #4

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.5257. Min Act: -0.0000

Data Index: 746716 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.5389. Min Act: -0.0000

Data Index: 1389366 (Python Code)

Max Activating Token Index: 142

Text #6

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.5444. Min Act: -0.0000

Data Index: 1656023 (Python Code)

Max Activating Token Index: 346

Text #7

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.4120. Min Act: -0.0000

Data Index: 1439869 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.5878. Min Act: -0.0000

Data Index: 1458451 (Python Code)

Max Activating Token Index: 50

Text #9

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.5137. Min Act: -0.0000

Data Index: 1590120 (Python Code)

Max Activating Token Index: 187

Text #10

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.5215. Min Act: -0.0000

Data Index: 1377199 (Python Code)

Max Activating Token Index: 960

Text #11

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.5537. Min Act: -0.0000

Data Index: 1560107 (Python Code)

Max Activating Token Index: 255

Text #12

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.4824. Min Act: -0.0000

Data Index: 1601762 (Python Code)

Max Activating Token Index: 805

Text #13

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.4841. Min Act: -0.0000

Data Index: 1532368 (Python Code)

Max Activating Token Index: 99

Text #14

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.5348. Min Act: -0.0000

Data Index: 1601965 (Python Code)

Max Activating Token Index: 946

Text #15

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.4585. Min Act: -0.0000

Data Index: 1328248 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.5230. Min Act: -0.0000

Data Index: 1531982 (Python Code)

Max Activating Token Index: 304

Text #17

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.4590. Min Act: -0.0000

Data Index: 693520 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.3701. Min Act: -0.0000

Data Index: 991376 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 1.9291. Min Range: -1.9291

Max Act: 1.3972. Min Act: -0.0000

Data Index: 685032 (C4 (Web Text))

Max Activating Token Index: 19