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

Dataset: The Pile

Neuron 2137 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 9.6915. Min Range: -9.6915

Max Act: 9.6915. Min Act: -0.0000

Data Index: 478682 (The Pile)

Max Activating Token Index: 476

Text #1

Max Range: 9.6915. Min Range: -9.6915

Max Act: 9.5221. Min Act: -0.0000

Data Index: 1713030 (The Pile)

Max Activating Token Index: 829

Text #2

Max Range: 9.6915. Min Range: -9.6915

Max Act: 7.6937. Min Act: -0.0000

Data Index: 1201738 (The Pile)

Max Activating Token Index: 1009

Text #3

Max Range: 9.6915. Min Range: -9.6915

Max Act: 7.5787. Min Act: -0.0000

Data Index: 773157 (The Pile)

Max Activating Token Index: 599

Text #4

Max Range: 9.6915. Min Range: -9.6915

Max Act: 6.2287. Min Act: -0.0000

Data Index: 121412 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 9.6915. Min Range: -9.6915

Max Act: 7.3066. Min Act: -0.0000

Data Index: 1600103 (The Pile)

Max Activating Token Index: 960

Text #6

Max Range: 9.6915. Min Range: -9.6915

Max Act: 7.4759. Min Act: -0.0000

Data Index: 195357 (The Pile)

Max Activating Token Index: 374

Text #7

Max Range: 9.6915. Min Range: -9.6915

Max Act: 7.5800. Min Act: -0.0000

Data Index: 504853 (The Pile)

Max Activating Token Index: 719

Text #8

Max Range: 9.6915. Min Range: -9.6915

Max Act: 6.8417. Min Act: -0.0000

Data Index: 1447616 (The Pile)

Max Activating Token Index: 291

Text #9

Max Range: 9.6915. Min Range: -9.6915

Max Act: 7.3324. Min Act: -0.0000

Data Index: 1792408 (The Pile)

Max Activating Token Index: 218

Text #10

Max Range: 9.6915. Min Range: -9.6915

Max Act: 6.4325. Min Act: -0.0000

Data Index: 389845 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 9.6915. Min Range: -9.6915

Max Act: 6.7449. Min Act: -0.0000

Data Index: 418872 (The Pile)

Max Activating Token Index: 297

Text #12

Max Range: 9.6915. Min Range: -9.6915

Max Act: 7.1778. Min Act: -0.0000

Data Index: 693645 (The Pile)

Max Activating Token Index: 387

Text #13

Max Range: 9.6915. Min Range: -9.6915

Max Act: 6.7743. Min Act: -0.0000

Data Index: 347531 (The Pile)

Max Activating Token Index: 519

Text #14

Max Range: 9.6915. Min Range: -9.6915

Max Act: 6.7067. Min Act: -0.0000

Data Index: 1669245 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 9.6915. Min Range: -9.6915

Max Act: 6.6860. Min Act: -0.0000

Data Index: 1354822 (The Pile)

Max Activating Token Index: 425

Text #16

Max Range: 9.6915. Min Range: -9.6915

Max Act: 6.9839. Min Act: -0.0000

Data Index: 110974 (The Pile)

Max Activating Token Index: 604

Text #17

Max Range: 9.6915. Min Range: -9.6915

Max Act: 6.0968. Min Act: -0.0000

Data Index: 1809675 (The Pile)

Max Activating Token Index: 295

Text #18

Max Range: 9.6915. Min Range: -9.6915

Max Act: 6.4433. Min Act: -0.0000

Data Index: 1069465 (The Pile)

Max Activating Token Index: 635

Text #19

Max Range: 9.6915. Min Range: -9.6915

Max Act: 6.5424. Min Act: -0.0000

Data Index: 1792858 (The Pile)

Max Activating Token Index: 934