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

Dataset: The Pile

Neuron 706 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1348332 (The Pile)

Max Activating Token Index: 922

Text #1

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1662183 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1427616 (The Pile)

Max Activating Token Index: 405

Text #3

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5190. Min Act: -0.0000

Data Index: 859780 (The Pile)

Max Activating Token Index: 862

Text #4

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1185712 (The Pile)

Max Activating Token Index: 683

Text #5

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4864. Min Act: -0.0000

Data Index: 31366 (The Pile)

Max Activating Token Index: 346

Text #6

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4568. Min Act: -0.0000

Data Index: 542355 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1380631 (The Pile)

Max Activating Token Index: 417

Text #8

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4686. Min Act: -0.0000

Data Index: 632798 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4457. Min Act: -0.0000

Data Index: 671531 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1018573 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4267. Min Act: -0.0000

Data Index: 99119 (The Pile)

Max Activating Token Index: 525

Text #12

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4426. Min Act: -0.0000

Data Index: 488019 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1752738 (The Pile)

Max Activating Token Index: 49

Text #14

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4290. Min Act: -0.0000

Data Index: 1135990 (The Pile)

Max Activating Token Index: 373

Text #15

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1013931 (The Pile)

Max Activating Token Index: 594

Text #16

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4444. Min Act: -0.0000

Data Index: 186927 (The Pile)

Max Activating Token Index: 269

Text #17

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1081167 (The Pile)

Max Activating Token Index: 708

Text #18

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1700378 (The Pile)

Max Activating Token Index: 7

Text #19

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1284741 (The Pile)

Max Activating Token Index: 23