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

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

Neuron 2440 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.6003. Min Act: -0.0002

Data Index: 700273 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.6047. Min Act: -0.0002

Data Index: 1583055 (Python Code)

Max Activating Token Index: 799

Text #2

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5527. Min Act: -0.0002

Data Index: 895376 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5151. Min Act: -0.0002

Data Index: 1460139 (Python Code)

Max Activating Token Index: 172

Text #4

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5087. Min Act: -0.0002

Data Index: 1540461 (Python Code)

Max Activating Token Index: 749

Text #5

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5182. Min Act: -0.0002

Data Index: 1454412 (Python Code)

Max Activating Token Index: 21

Text #6

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5262. Min Act: -0.0002

Data Index: 86759 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5436. Min Act: -0.0002

Data Index: 1417832 (Python Code)

Max Activating Token Index: 202

Text #8

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4576. Min Act: -0.0002

Data Index: 1596469 (Python Code)

Max Activating Token Index: 783

Text #9

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5228. Min Act: -0.0002

Data Index: 1431273 (Python Code)

Max Activating Token Index: 677

Text #10

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5494. Min Act: -0.0002

Data Index: 1432550 (Python Code)

Max Activating Token Index: 510

Text #11

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4915. Min Act: -0.0002

Data Index: 1451159 (Python Code)

Max Activating Token Index: 493

Text #12

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5223. Min Act: -0.0002

Data Index: 1563884 (Python Code)

Max Activating Token Index: 17

Text #13

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5500. Min Act: -0.0002

Data Index: 1418030 (Python Code)

Max Activating Token Index: 265

Text #14

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4687. Min Act: -0.0002

Data Index: 1586298 (Python Code)

Max Activating Token Index: 426

Text #15

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4477. Min Act: -0.0002

Data Index: 1367240 (Python Code)

Max Activating Token Index: 763

Text #16

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4410. Min Act: -0.0002

Data Index: 1518572 (Python Code)

Max Activating Token Index: 344

Text #17

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5088. Min Act: -0.0002

Data Index: 1589027 (Python Code)

Max Activating Token Index: 491

Text #18

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.4872. Min Act: -0.0002

Data Index: 1499623 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 0.6047. Min Range: -0.6047

Max Act: 0.5357. Min Act: -0.0002

Data Index: 1420896 (Python Code)

Max Activating Token Index: 761