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

Dataset: The Pile

Neuron 460 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: 0.7376. Min Range: -0.7376

Max Act: 0.7376. Min Act: -0.0000

Data Index: 1866067 (The Pile)

Max Activating Token Index: 515

Text #1

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.6162. Min Act: -0.0000

Data Index: 850082 (The Pile)

Max Activating Token Index: 477

Text #2

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1617599 (The Pile)

Max Activating Token Index: 270

Text #3

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5755. Min Act: -0.0000

Data Index: 752838 (The Pile)

Max Activating Token Index: 617

Text #4

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1528387 (The Pile)

Max Activating Token Index: 374

Text #5

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1869853 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5436. Min Act: -0.0000

Data Index: 1305580 (The Pile)

Max Activating Token Index: 404

Text #7

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1097444 (The Pile)

Max Activating Token Index: 238

Text #8

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5326. Min Act: -0.0000

Data Index: 781284 (The Pile)

Max Activating Token Index: 265

Text #9

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1790886 (The Pile)

Max Activating Token Index: 405

Text #10

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5413. Min Act: -0.0000

Data Index: 282 (The Pile)

Max Activating Token Index: 693

Text #11

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1214768 (The Pile)

Max Activating Token Index: 308

Text #12

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1868162 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1463606 (The Pile)

Max Activating Token Index: 589

Text #14

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1708299 (The Pile)

Max Activating Token Index: 612

Text #15

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1786051 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5219. Min Act: -0.0000

Data Index: 865498 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1985925 (The Pile)

Max Activating Token Index: 371

Text #18

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5484. Min Act: -0.0000

Data Index: 434441 (The Pile)

Max Activating Token Index: 780

Text #19

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1381798 (The Pile)

Max Activating Token Index: 446