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

Dataset: The Pile

Neuron 439 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: 0.6468. Min Range: -0.6468

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1961527 (The Pile)

Max Activating Token Index: 793

Text #1

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.6186. Min Act: -0.0000

Data Index: 690558 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.6181. Min Act: -0.0000

Data Index: 199083 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1884801 (The Pile)

Max Activating Token Index: 744

Text #4

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1064607 (The Pile)

Max Activating Token Index: 471

Text #5

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5466. Min Act: -0.0000

Data Index: 894205 (The Pile)

Max Activating Token Index: 51

Text #6

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1121029 (The Pile)

Max Activating Token Index: 820

Text #7

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5382. Min Act: -0.0000

Data Index: 825866 (The Pile)

Max Activating Token Index: 496

Text #8

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4811. Min Act: -0.0000

Data Index: 374357 (The Pile)

Max Activating Token Index: 682

Text #9

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4894. Min Act: -0.0000

Data Index: 274607 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1973850 (The Pile)

Max Activating Token Index: 486

Text #11

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1600420 (The Pile)

Max Activating Token Index: 869

Text #12

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1964246 (The Pile)

Max Activating Token Index: 238

Text #13

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1380848 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4458. Min Act: -0.0000

Data Index: 609654 (The Pile)

Max Activating Token Index: 474

Text #15

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1356339 (The Pile)

Max Activating Token Index: 854

Text #16

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4186. Min Act: -0.0000

Data Index: 45711 (The Pile)

Max Activating Token Index: 448

Text #17

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4253. Min Act: -0.0000

Data Index: 170522 (The Pile)

Max Activating Token Index: 705

Text #18

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1154833 (The Pile)

Max Activating Token Index: 72

Text #19

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.3785. Min Act: 0.0000

Data Index: 336707 (The Pile)

Max Activating Token Index: 450