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

Dataset: The Pile

Neuron 4224 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: 3.8839. Min Range: -3.8839

Max Act: 3.7114. Min Act: -0.0000

Data Index: 1215911 (The Pile)

Max Activating Token Index: 926

Text #1

Max Range: 3.8839. Min Range: -3.8839

Max Act: 3.8839. Min Act: -0.0000

Data Index: 1094927 (The Pile)

Max Activating Token Index: 344

Text #2

Max Range: 3.8839. Min Range: -3.8839

Max Act: 3.5948. Min Act: -0.0000

Data Index: 1103950 (The Pile)

Max Activating Token Index: 230

Text #3

Max Range: 3.8839. Min Range: -3.8839

Max Act: 3.7934. Min Act: -0.0000

Data Index: 1436924 (The Pile)

Max Activating Token Index: 568

Text #4

Max Range: 3.8839. Min Range: -3.8839

Max Act: 3.8428. Min Act: -0.0000

Data Index: 353900 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 3.8839. Min Range: -3.8839

Max Act: 3.3719. Min Act: -0.0000

Data Index: 1413086 (The Pile)

Max Activating Token Index: 281

Text #6

Max Range: 3.8839. Min Range: -3.8839

Max Act: 3.4648. Min Act: -0.0000

Data Index: 1104979 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 3.8839. Min Range: -3.8839

Max Act: 3.2021. Min Act: -0.0000

Data Index: 868207 (The Pile)

Max Activating Token Index: 581

Text #8

Max Range: 3.8839. Min Range: -3.8839

Max Act: 3.3059. Min Act: -0.0000

Data Index: 267866 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 3.8839. Min Range: -3.8839

Max Act: 3.3134. Min Act: -0.0000

Data Index: 1513191 (The Pile)

Max Activating Token Index: 85

Text #10

Max Range: 3.8839. Min Range: -3.8839

Max Act: 3.2644. Min Act: -0.0000

Data Index: 61329 (The Pile)

Max Activating Token Index: 105

Text #11

Max Range: 3.8839. Min Range: -3.8839

Max Act: 3.1361. Min Act: -0.0000

Data Index: 521173 (The Pile)

Max Activating Token Index: 201

Text #12

Max Range: 3.8839. Min Range: -3.8839

Max Act: 2.5671. Min Act: -0.0000

Data Index: 122497 (The Pile)

Max Activating Token Index: 722

Text #13

Max Range: 3.8839. Min Range: -3.8839

Max Act: 2.9482. Min Act: -0.0000

Data Index: 1841415 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 3.8839. Min Range: -3.8839

Max Act: 3.2413. Min Act: -0.0000

Data Index: 1505670 (The Pile)

Max Activating Token Index: 81

Text #15

Max Range: 3.8839. Min Range: -3.8839

Max Act: 2.9344. Min Act: -0.0000

Data Index: 1499874 (The Pile)

Max Activating Token Index: 504

Text #16

Max Range: 3.8839. Min Range: -3.8839

Max Act: 3.0754. Min Act: -0.0000

Data Index: 1800608 (The Pile)

Max Activating Token Index: 387

Text #17

Max Range: 3.8839. Min Range: -3.8839

Max Act: 2.9353. Min Act: -0.0000

Data Index: 491990 (The Pile)

Max Activating Token Index: 872

Text #18

Max Range: 3.8839. Min Range: -3.8839

Max Act: 3.1956. Min Act: -0.0000

Data Index: 1121346 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 3.8839. Min Range: -3.8839

Max Act: 2.9127. Min Act: -0.0000

Data Index: 1223029 (The Pile)

Max Activating Token Index: 276