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

Dataset: The Pile

Neuron 4804 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: 0.5876. Min Range: -0.5876

Max Act: 0.5730. Min Act: -0.0000

Data Index: 560257 (The Pile)

Max Activating Token Index: 533

Text #1

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1232388 (The Pile)

Max Activating Token Index: 364

Text #2

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.5876. Min Act: -0.0000

Data Index: 1571858 (The Pile)

Max Activating Token Index: 249

Text #3

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.5189. Min Act: -0.0000

Data Index: 384970 (The Pile)

Max Activating Token Index: 725

Text #4

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.5188. Min Act: -0.0000

Data Index: 1386868 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.5311. Min Act: -0.0000

Data Index: 23129 (The Pile)

Max Activating Token Index: 203

Text #6

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1543810 (The Pile)

Max Activating Token Index: 861

Text #7

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4795. Min Act: -0.0000

Data Index: 290291 (The Pile)

Max Activating Token Index: 656

Text #8

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1416395 (The Pile)

Max Activating Token Index: 665

Text #9

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4775. Min Act: -0.0000

Data Index: 607946 (The Pile)

Max Activating Token Index: 405

Text #10

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1051214 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1284768 (The Pile)

Max Activating Token Index: 719

Text #12

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1934033 (The Pile)

Max Activating Token Index: 706

Text #13

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1569802 (The Pile)

Max Activating Token Index: 885

Text #14

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4281. Min Act: -0.0000

Data Index: 786117 (The Pile)

Max Activating Token Index: 838

Text #15

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4366. Min Act: -0.0000

Data Index: 158404 (The Pile)

Max Activating Token Index: 845

Text #16

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1976655 (The Pile)

Max Activating Token Index: 272

Text #17

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1457938 (The Pile)

Max Activating Token Index: 533

Text #18

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1883124 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4117. Min Act: -0.0000

Data Index: 591888 (The Pile)

Max Activating Token Index: 842