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

Dataset: The Pile

Neuron 4268 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1792. Min Range: -1.1792

Max Act: 1.1792. Min Act: -0.0000

Data Index: 1009648 (The Pile)

Max Activating Token Index: 653

Text #1

Max Range: 1.1792. Min Range: -1.1792

Max Act: 1.0332. Min Act: -0.0000

Data Index: 256464 (The Pile)

Max Activating Token Index: 594

Text #2

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1572207 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1907893 (The Pile)

Max Activating Token Index: 483

Text #4

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1450059 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1181765 (The Pile)

Max Activating Token Index: 170

Text #6

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1143198 (The Pile)

Max Activating Token Index: 826

Text #7

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.7440. Min Act: -0.0000

Data Index: 1351192 (The Pile)

Max Activating Token Index: 790

Text #8

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.6363. Min Act: -0.0000

Data Index: 556297 (The Pile)

Max Activating Token Index: 258

Text #9

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.6524. Min Act: -0.0000

Data Index: 1467406 (The Pile)

Max Activating Token Index: 900

Text #10

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.6581. Min Act: -0.0000

Data Index: 412074 (The Pile)

Max Activating Token Index: 996

Text #11

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1242782 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.6667. Min Act: -0.0000

Data Index: 990188 (The Pile)

Max Activating Token Index: 628

Text #13

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1683820 (The Pile)

Max Activating Token Index: 65

Text #14

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1502147 (The Pile)

Max Activating Token Index: 376

Text #15

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.5684. Min Act: -0.0000

Data Index: 161087 (The Pile)

Max Activating Token Index: 87

Text #16

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.5758. Min Act: -0.0000

Data Index: 935383 (The Pile)

Max Activating Token Index: 513

Text #17

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.6626. Min Act: -0.0000

Data Index: 59185 (The Pile)

Max Activating Token Index: 250

Text #18

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1726121 (The Pile)

Max Activating Token Index: 890

Text #19

Max Range: 1.1792. Min Range: -1.1792

Max Act: 0.5849. Min Act: -0.0000

Data Index: 552042 (The Pile)

Max Activating Token Index: 975