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

Dataset: The Pile

Neuron 629 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: 0.9613. Min Range: -0.9613

Max Act: 0.9613. Min Act: -0.0000

Data Index: 124313 (The Pile)

Max Activating Token Index: 655

Text #1

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.8413. Min Act: -0.0000

Data Index: 828131 (The Pile)

Max Activating Token Index: 522

Text #2

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.6255. Min Act: -0.0000

Data Index: 524495 (The Pile)

Max Activating Token Index: 893

Text #3

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1973607 (The Pile)

Max Activating Token Index: 746

Text #4

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.6766. Min Act: -0.0000

Data Index: 34525 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.6168. Min Act: -0.0000

Data Index: 436549 (The Pile)

Max Activating Token Index: 77

Text #6

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1917445 (The Pile)

Max Activating Token Index: 555

Text #7

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1230742 (The Pile)

Max Activating Token Index: 436

Text #8

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1945597 (The Pile)

Max Activating Token Index: 90

Text #9

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.6247. Min Act: -0.0000

Data Index: 248468 (The Pile)

Max Activating Token Index: 809

Text #10

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.5700. Min Act: -0.0000

Data Index: 179477 (The Pile)

Max Activating Token Index: 511

Text #11

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.5512. Min Act: -0.0000

Data Index: 634047 (The Pile)

Max Activating Token Index: 504

Text #12

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1824056 (The Pile)

Max Activating Token Index: 605

Text #13

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.5548. Min Act: -0.0000

Data Index: 127458 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1943838 (The Pile)

Max Activating Token Index: 406

Text #15

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.5140. Min Act: -0.0000

Data Index: 827606 (The Pile)

Max Activating Token Index: 156

Text #16

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.5276. Min Act: -0.0000

Data Index: 707661 (The Pile)

Max Activating Token Index: 42

Text #17

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1467226 (The Pile)

Max Activating Token Index: 336

Text #18

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.4953. Min Act: -0.0000

Data Index: 374851 (The Pile)

Max Activating Token Index: 293

Text #19

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1312026 (The Pile)

Max Activating Token Index: 399