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

Dataset: The Pile

Neuron 697 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.6634. Min Act: -0.0000

Data Index: 306489 (The Pile)

Max Activating Token Index: 203

Text #1

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5361. Min Act: -0.0000

Data Index: 640735 (The Pile)

Max Activating Token Index: 924

Text #2

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5655. Min Act: -0.0000

Data Index: 788368 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5660. Min Act: -0.0000

Data Index: 668777 (The Pile)

Max Activating Token Index: 265

Text #4

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.6350. Min Act: -0.0000

Data Index: 1937150 (The Pile)

Max Activating Token Index: 430

Text #5

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1826893 (The Pile)

Max Activating Token Index: 156

Text #6

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5052. Min Act: -0.0000

Data Index: 876370 (The Pile)

Max Activating Token Index: 758

Text #7

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5902. Min Act: -0.0000

Data Index: 41872 (The Pile)

Max Activating Token Index: 353

Text #8

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1845290 (The Pile)

Max Activating Token Index: 480

Text #9

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1464202 (The Pile)

Max Activating Token Index: 97

Text #10

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5409. Min Act: -0.0000

Data Index: 261125 (The Pile)

Max Activating Token Index: 309

Text #11

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1069415 (The Pile)

Max Activating Token Index: 483

Text #12

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1334608 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5290. Min Act: -0.0000

Data Index: 1726064 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1241202 (The Pile)

Max Activating Token Index: 971

Text #15

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5345. Min Act: -0.0000

Data Index: 810102 (The Pile)

Max Activating Token Index: 765

Text #16

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4530. Min Act: -0.0000

Data Index: 226589 (The Pile)

Max Activating Token Index: 943

Text #17

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5171. Min Act: -0.0000

Data Index: 1418398 (The Pile)

Max Activating Token Index: 502

Text #18

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1229200 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4915. Min Act: -0.0000

Data Index: 1695477 (The Pile)

Max Activating Token Index: 173