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

Dataset: The Pile

Neuron 4592 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: 0.5349. Min Range: -0.5349

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1919415 (The Pile)

Max Activating Token Index: 826

Text #1

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1988783 (The Pile)

Max Activating Token Index: 568

Text #2

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.5174. Min Act: 0.0000

Data Index: 279890 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4403. Min Act: -0.0000

Data Index: 912262 (The Pile)

Max Activating Token Index: 553

Text #4

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4680. Min Act: -0.0000

Data Index: 55107 (The Pile)

Max Activating Token Index: 894

Text #5

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4476. Min Act: -0.0000

Data Index: 580537 (The Pile)

Max Activating Token Index: 572

Text #6

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1423625 (The Pile)

Max Activating Token Index: 276

Text #7

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1544889 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1208057 (The Pile)

Max Activating Token Index: 787

Text #9

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1933204 (The Pile)

Max Activating Token Index: 552

Text #10

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4311. Min Act: -0.0000

Data Index: 364146 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1462358 (The Pile)

Max Activating Token Index: 602

Text #12

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4366. Min Act: -0.0000

Data Index: 569027 (The Pile)

Max Activating Token Index: 218

Text #13

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1638397 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1385200 (The Pile)

Max Activating Token Index: 726

Text #15

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.3972. Min Act: -0.0000

Data Index: 1012083 (The Pile)

Max Activating Token Index: 987

Text #16

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4058. Min Act: -0.0000

Data Index: 1831937 (The Pile)

Max Activating Token Index: 654

Text #17

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4008. Min Act: -0.0000

Data Index: 1344015 (The Pile)

Max Activating Token Index: 783

Text #18

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4060. Min Act: -0.0000

Data Index: 316155 (The Pile)

Max Activating Token Index: 1002

Text #19

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1356767 (The Pile)

Max Activating Token Index: 894