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

Dataset: The Pile

Neuron 3511 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.3761. Min Act: -0.0000

Data Index: 1771255 (The Pile)

Max Activating Token Index: 532

Text #1

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.3018. Min Act: -0.0000

Data Index: 1672660 (The Pile)

Max Activating Token Index: 312

Text #2

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.2495. Min Act: -0.0000

Data Index: 1475509 (The Pile)

Max Activating Token Index: 713

Text #3

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.1722. Min Act: -0.0000

Data Index: 1672887 (The Pile)

Max Activating Token Index: 109

Text #4

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.1770. Min Act: -0.0000

Data Index: 156583 (The Pile)

Max Activating Token Index: 282

Text #5

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.1780. Min Act: -0.0000

Data Index: 1734472 (The Pile)

Max Activating Token Index: 633

Text #6

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.0802. Min Act: -0.0000

Data Index: 536217 (The Pile)

Max Activating Token Index: 516

Text #7

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.0980. Min Act: -0.0000

Data Index: 1950692 (The Pile)

Max Activating Token Index: 330

Text #8

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.1248. Min Act: -0.0000

Data Index: 769473 (The Pile)

Max Activating Token Index: 1008

Text #9

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.0731. Min Act: -0.0000

Data Index: 712896 (The Pile)

Max Activating Token Index: 540

Text #10

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.9707. Min Act: -0.0000

Data Index: 1419082 (The Pile)

Max Activating Token Index: 638

Text #11

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.8885. Min Act: -0.0000

Data Index: 210404 (The Pile)

Max Activating Token Index: 973

Text #12

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.0444. Min Act: -0.0000

Data Index: 359528 (The Pile)

Max Activating Token Index: 324

Text #13

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.0645. Min Act: -0.0000

Data Index: 1754133 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1442451 (The Pile)

Max Activating Token Index: 744

Text #15

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.0722. Min Act: -0.0000

Data Index: 270003 (The Pile)

Max Activating Token Index: 123

Text #16

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.1305. Min Act: -0.0000

Data Index: 742282 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.9404. Min Act: -0.0000

Data Index: 996975 (The Pile)

Max Activating Token Index: 282

Text #18

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.0435. Min Act: -0.0000

Data Index: 1731433 (The Pile)

Max Activating Token Index: 949

Text #19

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.9732. Min Act: -0.0000

Data Index: 1089918 (The Pile)

Max Activating Token Index: 16