Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2056 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1848396 (The Pile)

Max Activating Token Index: 901

Text #1

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.9109. Min Act: -0.0000

Data Index: 1132359 (The Pile)

Max Activating Token Index: 676

Text #2

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8424. Min Act: -0.0000

Data Index: 995439 (The Pile)

Max Activating Token Index: 577

Text #3

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8106. Min Act: -0.0000

Data Index: 23396 (The Pile)

Max Activating Token Index: 878

Text #4

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8124. Min Act: -0.0000

Data Index: 404417 (The Pile)

Max Activating Token Index: 293

Text #5

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1143201 (The Pile)

Max Activating Token Index: 640

Text #6

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7778. Min Act: -0.0000

Data Index: 295736 (The Pile)

Max Activating Token Index: 1012

Text #7

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7314. Min Act: -0.0000

Data Index: 611521 (The Pile)

Max Activating Token Index: 935

Text #8

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1842720 (The Pile)

Max Activating Token Index: 278

Text #9

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8023. Min Act: -0.0000

Data Index: 521810 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1827044 (The Pile)

Max Activating Token Index: 419

Text #11

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7281. Min Act: -0.0000

Data Index: 9109 (The Pile)

Max Activating Token Index: 323

Text #12

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7049. Min Act: -0.0000

Data Index: 1707824 (The Pile)

Max Activating Token Index: 622

Text #13

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1381042 (The Pile)

Max Activating Token Index: 104

Text #14

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7443. Min Act: -0.0000

Data Index: 85890 (The Pile)

Max Activating Token Index: 373

Text #15

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7346. Min Act: -0.0000

Data Index: 1772368 (The Pile)

Max Activating Token Index: 885

Text #16

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7340. Min Act: -0.0000

Data Index: 50721 (The Pile)

Max Activating Token Index: 568

Text #17

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1643798 (The Pile)

Max Activating Token Index: 900

Text #18

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1648367 (The Pile)

Max Activating Token Index: 316

Text #19

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.6931. Min Act: -0.0000

Data Index: 208264 (The Pile)

Max Activating Token Index: 215