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

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

Neuron 343 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1598987 (Python Code)

Max Activating Token Index: 264

Text #1

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6923. Min Act: -0.0000

Data Index: 1047767 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1620584 (Python Code)

Max Activating Token Index: 67

Text #3

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1374742 (Python Code)

Max Activating Token Index: 258

Text #4

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5864. Min Act: -0.0000

Data Index: 545366 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1161067 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5641. Min Act: -0.0000

Data Index: 450149 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1350196 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5705. Min Act: -0.0000

Data Index: 50340 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6455. Min Act: -0.0000

Data Index: 426936 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5337. Min Act: -0.0000

Data Index: 204023 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5236. Min Act: -0.0000

Data Index: 71742 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5484. Min Act: -0.0000

Data Index: 542074 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5681. Min Act: -0.0000

Data Index: 511056 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1002005 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5699. Min Act: -0.0000

Data Index: 177980 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1213667 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5595. Min Act: -0.0000

Data Index: 640207 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5729. Min Act: -0.0000

Data Index: 207327 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5291. Min Act: -0.0000

Data Index: 188200 (C4 (Web Text))

Max Activating Token Index: 826