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

Dataset: The Pile

Neuron 706 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.3343. Min Act: -0.0000

Data Index: 1609308 (The Pile)

Max Activating Token Index: 541

Text #1

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.2917. Min Act: -0.0000

Data Index: 372505 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.9466. Min Act: -0.0000

Data Index: 1517306 (The Pile)

Max Activating Token Index: 638

Text #3

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.7782. Min Act: -0.0000

Data Index: 580314 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.6777. Min Act: -0.0000

Data Index: 354793 (The Pile)

Max Activating Token Index: 746

Text #5

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.6739. Min Act: -0.0000

Data Index: 918605 (The Pile)

Max Activating Token Index: 138

Text #6

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.6446. Min Act: -0.0000

Data Index: 760011 (The Pile)

Max Activating Token Index: 482

Text #7

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1707641 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.6587. Min Act: -0.0000

Data Index: 984756 (The Pile)

Max Activating Token Index: 1001

Text #9

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.6462. Min Act: -0.0000

Data Index: 815130 (The Pile)

Max Activating Token Index: 856

Text #10

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1346589 (The Pile)

Max Activating Token Index: 369

Text #11

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1530266 (The Pile)

Max Activating Token Index: 747

Text #12

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1446554 (The Pile)

Max Activating Token Index: 766

Text #13

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1171947 (The Pile)

Max Activating Token Index: 92

Text #14

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.5897. Min Act: -0.0000

Data Index: 606703 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1511069 (The Pile)

Max Activating Token Index: 114

Text #16

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1978261 (The Pile)

Max Activating Token Index: 231

Text #17

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.5444. Min Act: -0.0000

Data Index: 542319 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.5075. Min Act: -0.0000

Data Index: 366044 (The Pile)

Max Activating Token Index: 932

Text #19

Max Range: 1.3343. Min Range: -1.3343

Max Act: 0.5196. Min Act: 0.0000

Data Index: 1720242 (The Pile)

Max Activating Token Index: 803