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

Dataset: The Pile

Neuron 319 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: 1.5196. Min Range: -1.5196

Max Act: 1.5196. Min Act: -0.0000

Data Index: 958255 (The Pile)

Max Activating Token Index: 443

Text #1

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.3567. Min Act: -0.0000

Data Index: 1168227 (The Pile)

Max Activating Token Index: 868

Text #2

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.2627. Min Act: -0.0000

Data Index: 462691 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.1640. Min Act: -0.0000

Data Index: 638143 (The Pile)

Max Activating Token Index: 985

Text #4

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.2245. Min Act: -0.0000

Data Index: 621061 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.1736. Min Act: -0.0000

Data Index: 807427 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.2071. Min Act: -0.0000

Data Index: 1632749 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.1680. Min Act: -0.0000

Data Index: 231999 (The Pile)

Max Activating Token Index: 656

Text #8

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.0990. Min Act: -0.0000

Data Index: 850282 (The Pile)

Max Activating Token Index: 203

Text #9

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.0715. Min Act: -0.0000

Data Index: 443353 (The Pile)

Max Activating Token Index: 453

Text #10

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1597082 (The Pile)

Max Activating Token Index: 284

Text #11

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1210446 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.9627. Min Act: -0.0000

Data Index: 1928955 (The Pile)

Max Activating Token Index: 174

Text #13

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.9553. Min Act: -0.0000

Data Index: 772155 (The Pile)

Max Activating Token Index: 569

Text #14

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.9793. Min Act: -0.0000

Data Index: 911080 (The Pile)

Max Activating Token Index: 285

Text #15

Max Range: 1.5196. Min Range: -1.5196

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1216953 (The Pile)

Max Activating Token Index: 1022

Text #16

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.9788. Min Act: -0.0000

Data Index: 1385077 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.9775. Min Act: -0.0000

Data Index: 1572115 (The Pile)

Max Activating Token Index: 847

Text #18

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.9847. Min Act: -0.0000

Data Index: 148301 (The Pile)

Max Activating Token Index: 734

Text #19

Max Range: 1.5196. Min Range: -1.5196

Max Act: 0.9577. Min Act: -0.0000

Data Index: 516959 (The Pile)

Max Activating Token Index: 419