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

Dataset: The Pile

Neuron 756 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: 4.6017. Min Range: -4.6017

Max Act: 4.6017. Min Act: -0.0000

Data Index: 769839 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.3112. Min Act: -0.0000

Data Index: 1801066 (The Pile)

Max Activating Token Index: 672

Text #2

Max Range: 4.6017. Min Range: -4.6017

Max Act: 3.9429. Min Act: -0.0000

Data Index: 21142 (The Pile)

Max Activating Token Index: 820

Text #3

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.0770. Min Act: -0.0000

Data Index: 1512085 (The Pile)

Max Activating Token Index: 353

Text #4

Max Range: 4.6017. Min Range: -4.6017

Max Act: 3.7206. Min Act: -0.0000

Data Index: 367268 (The Pile)

Max Activating Token Index: 800

Text #5

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.0308. Min Act: -0.0000

Data Index: 314502 (The Pile)

Max Activating Token Index: 631

Text #6

Max Range: 4.6017. Min Range: -4.6017

Max Act: 3.9612. Min Act: -0.0000

Data Index: 463286 (The Pile)

Max Activating Token Index: 202

Text #7

Max Range: 4.6017. Min Range: -4.6017

Max Act: 3.7284. Min Act: -0.0000

Data Index: 823307 (The Pile)

Max Activating Token Index: 748

Text #8

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.2154. Min Act: -0.0000

Data Index: 1512467 (The Pile)

Max Activating Token Index: 617

Text #9

Max Range: 4.6017. Min Range: -4.6017

Max Act: 3.7887. Min Act: -0.0000

Data Index: 532202 (The Pile)

Max Activating Token Index: 277

Text #10

Max Range: 4.6017. Min Range: -4.6017

Max Act: 3.1587. Min Act: -0.0000

Data Index: 1830210 (The Pile)

Max Activating Token Index: 933

Text #11

Max Range: 4.6017. Min Range: -4.6017

Max Act: 3.7262. Min Act: -0.0000

Data Index: 1481783 (The Pile)

Max Activating Token Index: 389

Text #12

Max Range: 4.6017. Min Range: -4.6017

Max Act: 3.5530. Min Act: -0.0000

Data Index: 573495 (The Pile)

Max Activating Token Index: 390

Text #13

Max Range: 4.6017. Min Range: -4.6017

Max Act: 3.4594. Min Act: -0.0000

Data Index: 812355 (The Pile)

Max Activating Token Index: 76

Text #14

Max Range: 4.6017. Min Range: -4.6017

Max Act: 3.3105. Min Act: -0.0000

Data Index: 1563607 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 4.6017. Min Range: -4.6017

Max Act: 3.4285. Min Act: -0.0000

Data Index: 1550942 (The Pile)

Max Activating Token Index: 30

Text #16

Max Range: 4.6017. Min Range: -4.6017

Max Act: 3.3592. Min Act: -0.0000

Data Index: 1387347 (The Pile)

Max Activating Token Index: 578

Text #17

Max Range: 4.6017. Min Range: -4.6017

Max Act: 3.2912. Min Act: -0.0000

Data Index: 284072 (The Pile)

Max Activating Token Index: 561

Text #18

Max Range: 4.6017. Min Range: -4.6017

Max Act: 3.1220. Min Act: -0.0000

Data Index: 1318168 (The Pile)

Max Activating Token Index: 696

Text #19

Max Range: 4.6017. Min Range: -4.6017

Max Act: 3.2656. Min Act: -0.0000

Data Index: 1011009 (The Pile)

Max Activating Token Index: 561