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

Dataset: The Pile

Neuron 2679 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: 0.6832. Min Range: -0.6832

Max Act: 0.6832. Min Act: -0.0000

Data Index: 686473 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1627580 (The Pile)

Max Activating Token Index: 11

Text #2

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.6528. Min Act: -0.0000

Data Index: 140246 (The Pile)

Max Activating Token Index: 436

Text #3

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1631874 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5603. Min Act: -0.0000

Data Index: 392648 (The Pile)

Max Activating Token Index: 288

Text #5

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1014563 (The Pile)

Max Activating Token Index: 496

Text #6

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1078105 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1481047 (The Pile)

Max Activating Token Index: 626

Text #8

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5193. Min Act: -0.0000

Data Index: 1021806 (The Pile)

Max Activating Token Index: 396

Text #9

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1645415 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1673989 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5225. Min Act: -0.0000

Data Index: 793649 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5106. Min Act: -0.0000

Data Index: 76164 (The Pile)

Max Activating Token Index: 711

Text #13

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5112. Min Act: -0.0000

Data Index: 819259 (The Pile)

Max Activating Token Index: 155

Text #14

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4913. Min Act: -0.0000

Data Index: 695346 (The Pile)

Max Activating Token Index: 329

Text #15

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1382651 (The Pile)

Max Activating Token Index: 465

Text #16

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1956762 (The Pile)

Max Activating Token Index: 26

Text #17

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5211. Min Act: -0.0000

Data Index: 473149 (The Pile)

Max Activating Token Index: 276

Text #18

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5033. Min Act: -0.0000

Data Index: 319662 (The Pile)

Max Activating Token Index: 410

Text #19

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5033. Min Act: -0.0000

Data Index: 677206 (The Pile)

Max Activating Token Index: 235