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

Dataset: The Pile

Neuron 659 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: 1.5710. Min Range: -1.5710

Max Act: 1.5710. Min Act: -0.0000

Data Index: 767712 (The Pile)

Max Activating Token Index: 483

Text #1

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4410. Min Act: -0.0000

Data Index: 1988473 (The Pile)

Max Activating Token Index: 637

Text #2

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.3515. Min Act: -0.0000

Data Index: 743834 (The Pile)

Max Activating Token Index: 513

Text #3

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4180. Min Act: -0.0000

Data Index: 745216 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.3606. Min Act: -0.0000

Data Index: 1706092 (The Pile)

Max Activating Token Index: 902

Text #5

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.3454. Min Act: -0.0000

Data Index: 489223 (The Pile)

Max Activating Token Index: 319

Text #6

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4837. Min Act: -0.0000

Data Index: 952531 (The Pile)

Max Activating Token Index: 644

Text #7

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.2166. Min Act: -0.0000

Data Index: 1617174 (The Pile)

Max Activating Token Index: 504

Text #8

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4094. Min Act: -0.0000

Data Index: 261378 (The Pile)

Max Activating Token Index: 902

Text #9

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.3684. Min Act: -0.0000

Data Index: 654703 (The Pile)

Max Activating Token Index: 671

Text #10

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.3364. Min Act: -0.0000

Data Index: 1996119 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.2878. Min Act: -0.0000

Data Index: 405428 (The Pile)

Max Activating Token Index: 678

Text #12

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.3410. Min Act: -0.0000

Data Index: 1212692 (The Pile)

Max Activating Token Index: 320

Text #13

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.2539. Min Act: -0.0000

Data Index: 175323 (The Pile)

Max Activating Token Index: 851

Text #14

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.2234. Min Act: -0.0000

Data Index: 396101 (The Pile)

Max Activating Token Index: 818

Text #15

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.3156. Min Act: -0.0000

Data Index: 1090291 (The Pile)

Max Activating Token Index: 559

Text #16

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.2203. Min Act: -0.0000

Data Index: 210719 (The Pile)

Max Activating Token Index: 469

Text #17

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.2233. Min Act: -0.0000

Data Index: 1475463 (The Pile)

Max Activating Token Index: 401

Text #18

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.3042. Min Act: -0.0000

Data Index: 993368 (The Pile)

Max Activating Token Index: 575

Text #19

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.1163. Min Act: -0.0000

Data Index: 1858579 (The Pile)

Max Activating Token Index: 980