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

Dataset: The Pile

Neuron 3905 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: 0.7613. Min Range: -0.7613

Max Act: 0.7137. Min Act: -0.0000

Data Index: 515343 (The Pile)

Max Activating Token Index: 397

Text #1

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.7613. Min Act: -0.0000

Data Index: 1373617 (The Pile)

Max Activating Token Index: 517

Text #2

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6842. Min Act: -0.0000

Data Index: 755041 (The Pile)

Max Activating Token Index: 116

Text #3

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6808. Min Act: -0.0000

Data Index: 396713 (The Pile)

Max Activating Token Index: 912

Text #4

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1474134 (The Pile)

Max Activating Token Index: 156

Text #5

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1037775 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1669913 (The Pile)

Max Activating Token Index: 511

Text #7

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1922966 (The Pile)

Max Activating Token Index: 512

Text #8

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6304. Min Act: -0.0000

Data Index: 182235 (The Pile)

Max Activating Token Index: 31

Text #9

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6231. Min Act: -0.0000

Data Index: 267426 (The Pile)

Max Activating Token Index: 170

Text #10

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1927956 (The Pile)

Max Activating Token Index: 991

Text #11

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6001. Min Act: -0.0000

Data Index: 389919 (The Pile)

Max Activating Token Index: 361

Text #12

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1825620 (The Pile)

Max Activating Token Index: 286

Text #13

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5504. Min Act: -0.0000

Data Index: 315407 (The Pile)

Max Activating Token Index: 974

Text #14

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1840291 (The Pile)

Max Activating Token Index: 263

Text #15

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1555601 (The Pile)

Max Activating Token Index: 735

Text #16

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5760. Min Act: 0.0000

Data Index: 1529855 (The Pile)

Max Activating Token Index: 351

Text #17

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1683793 (The Pile)

Max Activating Token Index: 387

Text #18

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1661590 (The Pile)

Max Activating Token Index: 374

Text #19

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1087085 (The Pile)

Max Activating Token Index: 489