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

Dataset: The Pile

Neuron 1092 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: 0.6953. Min Range: -0.6953

Max Act: 0.6953. Min Act: -0.0000

Data Index: 419118 (The Pile)

Max Activating Token Index: 388

Text #1

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1119742 (The Pile)

Max Activating Token Index: 678

Text #2

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6164. Min Act: -0.0000

Data Index: 864428 (The Pile)

Max Activating Token Index: 372

Text #3

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1612150 (The Pile)

Max Activating Token Index: 445

Text #4

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6031. Min Act: -0.0000

Data Index: 164014 (The Pile)

Max Activating Token Index: 266

Text #5

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1169848 (The Pile)

Max Activating Token Index: 846

Text #6

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6017. Min Act: -0.0000

Data Index: 284355 (The Pile)

Max Activating Token Index: 245

Text #7

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6355. Min Act: -0.0000

Data Index: 1508539 (The Pile)

Max Activating Token Index: 609

Text #8

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5987. Min Act: -0.0000

Data Index: 588721 (The Pile)

Max Activating Token Index: 511

Text #9

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6273. Min Act: -0.0000

Data Index: 706770 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1550100 (The Pile)

Max Activating Token Index: 834

Text #11

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1469999 (The Pile)

Max Activating Token Index: 805

Text #12

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1023584 (The Pile)

Max Activating Token Index: 61

Text #13

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1444134 (The Pile)

Max Activating Token Index: 198

Text #14

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1417778 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5954. Min Act: -0.0000

Data Index: 123374 (The Pile)

Max Activating Token Index: 765

Text #16

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5806. Min Act: -0.0000

Data Index: 855723 (The Pile)

Max Activating Token Index: 918

Text #17

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5753. Min Act: -0.0000

Data Index: 1734769 (The Pile)

Max Activating Token Index: 700

Text #18

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5597. Min Act: -0.0000

Data Index: 963601 (The Pile)

Max Activating Token Index: 228

Text #19

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1613470 (The Pile)

Max Activating Token Index: 316