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

Dataset: The Pile

Neuron 4709 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: 0.8214. Min Range: -0.8214

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1260303 (The Pile)

Max Activating Token Index: 799

Text #1

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.8214. Min Act: -0.0000

Data Index: 661201 (The Pile)

Max Activating Token Index: 75

Text #2

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6994. Min Act: -0.0000

Data Index: 289856 (The Pile)

Max Activating Token Index: 334

Text #3

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1498983 (The Pile)

Max Activating Token Index: 500

Text #4

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.6626. Min Act: -0.0000

Data Index: 619763 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1913664 (The Pile)

Max Activating Token Index: 330

Text #6

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1140969 (The Pile)

Max Activating Token Index: 724

Text #7

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1899457 (The Pile)

Max Activating Token Index: 569

Text #8

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5147. Min Act: -0.0000

Data Index: 541747 (The Pile)

Max Activating Token Index: 849

Text #9

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1146564 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4354. Min Act: -0.0000

Data Index: 754973 (The Pile)

Max Activating Token Index: 65

Text #11

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4931. Min Act: -0.0000

Data Index: 62288 (The Pile)

Max Activating Token Index: 757

Text #12

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4886. Min Act: -0.0000

Data Index: 558384 (The Pile)

Max Activating Token Index: 9

Text #13

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4865. Min Act: -0.0000

Data Index: 127866 (The Pile)

Max Activating Token Index: 809

Text #14

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1240370 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1675429 (The Pile)

Max Activating Token Index: 948

Text #16

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4454. Min Act: -0.0000

Data Index: 770120 (The Pile)

Max Activating Token Index: 808

Text #17

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1362610 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4539. Min Act: -0.0000

Data Index: 83915 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1192371 (The Pile)

Max Activating Token Index: 507