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

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

Neuron 4464 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.5771. Min Act: -0.0000

Data Index: 1367483 (Python Code)

Max Activating Token Index: 259

Text #1

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.3770. Min Act: -0.0000

Data Index: 878113 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.4182. Min Act: -0.0000

Data Index: 1421924 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.3481. Min Act: -0.0000

Data Index: 1621497 (Python Code)

Max Activating Token Index: 516

Text #4

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.4207. Min Act: -0.0000

Data Index: 1470118 (Python Code)

Max Activating Token Index: 295

Text #5

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.3277. Min Act: -0.0000

Data Index: 1477062 (Python Code)

Max Activating Token Index: 457

Text #6

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.3254. Min Act: -0.0000

Data Index: 1361931 (Python Code)

Max Activating Token Index: 656

Text #7

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.3498. Min Act: -0.0000

Data Index: 1402460 (Python Code)

Max Activating Token Index: 155

Text #8

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.3520. Min Act: -0.0000

Data Index: 1401700 (Python Code)

Max Activating Token Index: 821

Text #9

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.3249. Min Act: -0.0000

Data Index: 1654281 (Python Code)

Max Activating Token Index: 154

Text #10

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.2225. Min Act: -0.0000

Data Index: 1485313 (Python Code)

Max Activating Token Index: 677

Text #11

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.2679. Min Act: -0.0000

Data Index: 1169345 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.2853. Min Act: -0.0000

Data Index: 1640234 (Python Code)

Max Activating Token Index: 506

Text #13

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.2423. Min Act: 0.0000

Data Index: 1449448 (Python Code)

Max Activating Token Index: 198

Text #14

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.2701. Min Act: -0.0000

Data Index: 1559660 (Python Code)

Max Activating Token Index: 409

Text #15

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.2582. Min Act: -0.0000

Data Index: 1468233 (Python Code)

Max Activating Token Index: 187

Text #16

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.2363. Min Act: -0.0000

Data Index: 1372160 (Python Code)

Max Activating Token Index: 15

Text #17

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.1850. Min Act: -0.0000

Data Index: 1379288 (Python Code)

Max Activating Token Index: 561

Text #18

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.2348. Min Act: -0.0000

Data Index: 1571857 (Python Code)

Max Activating Token Index: 520

Text #19

Max Range: 1.5771. Min Range: -1.5771

Max Act: 1.1973. Min Act: -0.0000

Data Index: 1436399 (Python Code)

Max Activating Token Index: 190