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

Dataset: The Pile

Neuron 4866 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.6608. Min Act: -0.0000

Data Index: 660355 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5719. Min Act: -0.0000

Data Index: 991158 (The Pile)

Max Activating Token Index: 895

Text #2

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1752377 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5125. Min Act: -0.0000

Data Index: 56134 (The Pile)

Max Activating Token Index: 385

Text #4

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1842805 (The Pile)

Max Activating Token Index: 44

Text #5

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5128. Min Act: -0.0000

Data Index: 791718 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5031. Min Act: -0.0000

Data Index: 309419 (The Pile)

Max Activating Token Index: 167

Text #7

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1988678 (The Pile)

Max Activating Token Index: 374

Text #8

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3772. Min Act: -0.0000

Data Index: 414502 (The Pile)

Max Activating Token Index: 277

Text #9

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5015. Min Act: -0.0000

Data Index: 357825 (The Pile)

Max Activating Token Index: 715

Text #10

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1396595 (The Pile)

Max Activating Token Index: 492

Text #11

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1731767 (The Pile)

Max Activating Token Index: 199

Text #12

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1167825 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1949427 (The Pile)

Max Activating Token Index: 864

Text #14

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4418. Min Act: -0.0000

Data Index: 837233 (The Pile)

Max Activating Token Index: 560

Text #15

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1807013 (The Pile)

Max Activating Token Index: 173

Text #16

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1071104 (The Pile)

Max Activating Token Index: 15

Text #17

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4493. Min Act: -0.0000

Data Index: 418925 (The Pile)

Max Activating Token Index: 134

Text #18

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4173. Min Act: -0.0000

Data Index: 1603802 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4201. Min Act: -0.0000

Data Index: 497004 (The Pile)

Max Activating Token Index: 241