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

Dataset: The Pile

Neuron 4814 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7286. Min Range: -1.7286

Max Act: 1.7286. Min Act: -0.0000

Data Index: 1363444 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 1.7286. Min Range: -1.7286

Max Act: 1.1700. Min Act: -0.0000

Data Index: 383636 (The Pile)

Max Activating Token Index: 370

Text #2

Max Range: 1.7286. Min Range: -1.7286

Max Act: 1.2726. Min Act: -0.0000

Data Index: 704395 (The Pile)

Max Activating Token Index: 762

Text #3

Max Range: 1.7286. Min Range: -1.7286

Max Act: 1.0831. Min Act: -0.0000

Data Index: 409755 (The Pile)

Max Activating Token Index: 83

Text #4

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.9202. Min Act: -0.0000

Data Index: 1790698 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.9905. Min Act: -0.0000

Data Index: 1686241 (The Pile)

Max Activating Token Index: 677

Text #6

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.9855. Min Act: -0.0000

Data Index: 1129812 (The Pile)

Max Activating Token Index: 79

Text #7

Max Range: 1.7286. Min Range: -1.7286

Max Act: 1.0406. Min Act: -0.0000

Data Index: 399489 (The Pile)

Max Activating Token Index: 299

Text #8

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.9702. Min Act: -0.0000

Data Index: 744404 (The Pile)

Max Activating Token Index: 435

Text #9

Max Range: 1.7286. Min Range: -1.7286

Max Act: 1.0854. Min Act: -0.0000

Data Index: 880497 (The Pile)

Max Activating Token Index: 397

Text #10

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.9851. Min Act: -0.0000

Data Index: 378717 (The Pile)

Max Activating Token Index: 159

Text #11

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.9819. Min Act: -0.0000

Data Index: 586384 (The Pile)

Max Activating Token Index: 755

Text #12

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.9809. Min Act: -0.0000

Data Index: 554436 (The Pile)

Max Activating Token Index: 66

Text #13

Max Range: 1.7286. Min Range: -1.7286

Max Act: 1.0301. Min Act: -0.0000

Data Index: 245820 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.9354. Min Act: -0.0000

Data Index: 1448969 (The Pile)

Max Activating Token Index: 696

Text #15

Max Range: 1.7286. Min Range: -1.7286

Max Act: 1.0288. Min Act: 0.0000

Data Index: 644213 (The Pile)

Max Activating Token Index: 377

Text #16

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1429046 (The Pile)

Max Activating Token Index: 154

Text #17

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1395055 (The Pile)

Max Activating Token Index: 803

Text #18

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.8230. Min Act: 0.0002

Data Index: 1973890 (The Pile)

Max Activating Token Index: 865

Text #19

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.9226. Min Act: -0.0000

Data Index: 437235 (The Pile)

Max Activating Token Index: 598