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

Dataset: The Pile

Neuron 4509 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: 1.5424. Min Range: -1.5424

Max Act: 1.5424. Min Act: -0.0000

Data Index: 918618 (The Pile)

Max Activating Token Index: 105

Text #1

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.3782. Min Act: -0.0000

Data Index: 264092 (The Pile)

Max Activating Token Index: 390

Text #2

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.3051. Min Act: -0.0000

Data Index: 1380700 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0632. Min Act: -0.0000

Data Index: 1002466 (The Pile)

Max Activating Token Index: 778

Text #4

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.2311. Min Act: -0.0000

Data Index: 1074174 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.2396. Min Act: -0.0000

Data Index: 538928 (The Pile)

Max Activating Token Index: 620

Text #6

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0517. Min Act: -0.0000

Data Index: 1601051 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.1089. Min Act: -0.0000

Data Index: 869267 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.1104. Min Act: -0.0000

Data Index: 1891578 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0992. Min Act: -0.0000

Data Index: 1027095 (The Pile)

Max Activating Token Index: 196

Text #10

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0963. Min Act: -0.0000

Data Index: 998800 (The Pile)

Max Activating Token Index: 312

Text #11

Max Range: 1.5424. Min Range: -1.5424

Max Act: 0.9987. Min Act: -0.0000

Data Index: 1771410 (The Pile)

Max Activating Token Index: 90

Text #12

Max Range: 1.5424. Min Range: -1.5424

Max Act: 0.9421. Min Act: -0.0000

Data Index: 127861 (The Pile)

Max Activating Token Index: 159

Text #13

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0779. Min Act: -0.0000

Data Index: 203190 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0813. Min Act: -0.0000

Data Index: 476336 (The Pile)

Max Activating Token Index: 850

Text #15

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0077. Min Act: -0.0000

Data Index: 141061 (The Pile)

Max Activating Token Index: 193

Text #16

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0408. Min Act: -0.0000

Data Index: 760001 (The Pile)

Max Activating Token Index: 973

Text #17

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0353. Min Act: -0.0000

Data Index: 929750 (The Pile)

Max Activating Token Index: 536

Text #18

Max Range: 1.5424. Min Range: -1.5424

Max Act: 0.9793. Min Act: -0.0000

Data Index: 664865 (The Pile)

Max Activating Token Index: 944

Text #19

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0617. Min Act: -0.0000

Data Index: 269299 (The Pile)

Max Activating Token Index: 1012