Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 531 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.7074. Min Act: -0.0000

Data Index: 1672219 (The Pile)

Max Activating Token Index: 37

Text #1

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1293568 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.6462. Min Act: -0.0000

Data Index: 425138 (The Pile)

Max Activating Token Index: 866

Text #3

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.6121. Min Act: -0.0000

Data Index: 205531 (The Pile)

Max Activating Token Index: 764

Text #4

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1049403 (The Pile)

Max Activating Token Index: 44

Text #5

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5947. Min Act: 0.0000

Data Index: 1836916 (The Pile)

Max Activating Token Index: 392

Text #6

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5746. Min Act: -0.0000

Data Index: 669527 (The Pile)

Max Activating Token Index: 646

Text #7

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1747694 (The Pile)

Max Activating Token Index: 542

Text #8

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1778048 (The Pile)

Max Activating Token Index: 142

Text #9

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1925412 (The Pile)

Max Activating Token Index: 124

Text #10

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1344578 (The Pile)

Max Activating Token Index: 968

Text #11

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5485. Min Act: -0.0000

Data Index: 755319 (The Pile)

Max Activating Token Index: 397

Text #12

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5446. Min Act: -0.0000

Data Index: 1442759 (The Pile)

Max Activating Token Index: 653

Text #13

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5439. Min Act: -0.0000

Data Index: 437729 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1152037 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5667. Min Act: 0.0000

Data Index: 1615789 (The Pile)

Max Activating Token Index: 634

Text #16

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1948039 (The Pile)

Max Activating Token Index: 131

Text #17

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1255077 (The Pile)

Max Activating Token Index: 102

Text #18

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1662331 (The Pile)

Max Activating Token Index: 73

Text #19

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5087. Min Act: -0.0000

Data Index: 58982 (The Pile)

Max Activating Token Index: 545