Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2416 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.8671. Min Act: -0.0000

Data Index: 203083 (The Pile)

Max Activating Token Index: 169

Text #1

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1843155 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.8298. Min Act: -0.0000

Data Index: 200134 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7320. Min Act: -0.0000

Data Index: 23670 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7111. Min Act: -0.0000

Data Index: 376776 (The Pile)

Max Activating Token Index: 493

Text #5

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1818567 (The Pile)

Max Activating Token Index: 687

Text #6

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7886. Min Act: -0.0000

Data Index: 642204 (The Pile)

Max Activating Token Index: 163

Text #7

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7797. Min Act: -0.0000

Data Index: 896331 (The Pile)

Max Activating Token Index: 642

Text #8

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1681386 (The Pile)

Max Activating Token Index: 427

Text #9

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1949400 (The Pile)

Max Activating Token Index: 471

Text #10

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6761. Min Act: 0.0000

Data Index: 1354301 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1426362 (The Pile)

Max Activating Token Index: 432

Text #12

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6732. Min Act: -0.0000

Data Index: 762771 (The Pile)

Max Activating Token Index: 629

Text #13

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6324. Min Act: -0.0000

Data Index: 547932 (The Pile)

Max Activating Token Index: 276

Text #14

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1151885 (The Pile)

Max Activating Token Index: 397

Text #15

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6492. Min Act: -0.0000

Data Index: 139922 (The Pile)

Max Activating Token Index: 933

Text #16

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6435. Min Act: -0.0000

Data Index: 937517 (The Pile)

Max Activating Token Index: 81

Text #17

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1198635 (The Pile)

Max Activating Token Index: 646

Text #18

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6184. Min Act: -0.0000

Data Index: 598674 (The Pile)

Max Activating Token Index: 136

Text #19

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.5902. Min Act: -0.0000

Data Index: 865760 (The Pile)

Max Activating Token Index: 697