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

Dataset: The Pile

Neuron 12 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: 0.5963. Min Range: -0.5963

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1831423 (The Pile)

Max Activating Token Index: 606

Text #1

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1307888 (The Pile)

Max Activating Token Index: 911

Text #2

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1608655 (The Pile)

Max Activating Token Index: 964

Text #3

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5409. Min Act: -0.0000

Data Index: 156094 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4835. Min Act: -0.0000

Data Index: 600831 (The Pile)

Max Activating Token Index: 497

Text #5

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5515. Min Act: -0.0000

Data Index: 1444757 (The Pile)

Max Activating Token Index: 617

Text #6

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1893716 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4712. Min Act: -0.0000

Data Index: 391657 (The Pile)

Max Activating Token Index: 542

Text #8

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4862. Min Act: -0.0000

Data Index: 754483 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1353533 (The Pile)

Max Activating Token Index: 523

Text #10

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1756122 (The Pile)

Max Activating Token Index: 163

Text #11

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1700026 (The Pile)

Max Activating Token Index: 339

Text #12

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5180. Min Act: -0.0000

Data Index: 343801 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4650. Min Act: -0.0000

Data Index: 153560 (The Pile)

Max Activating Token Index: 358

Text #14

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4742. Min Act: -0.0000

Data Index: 1852615 (The Pile)

Max Activating Token Index: 761

Text #15

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1651036 (The Pile)

Max Activating Token Index: 265

Text #16

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4691. Min Act: -0.0000

Data Index: 724481 (The Pile)

Max Activating Token Index: 814

Text #17

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4416. Min Act: -0.0000

Data Index: 230748 (The Pile)

Max Activating Token Index: 413

Text #18

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4613. Min Act: -0.0000

Data Index: 1254415 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4737. Min Act: -0.0000

Data Index: 1685618 (The Pile)

Max Activating Token Index: 414