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

Dataset: The Pile

Neuron 3642 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0253. Min Range: -1.0253

Max Act: 1.0253. Min Act: -0.0000

Data Index: 1998154 (The Pile)

Max Activating Token Index: 32

Text #1

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.9819. Min Act: -0.0000

Data Index: 709017 (The Pile)

Max Activating Token Index: 176

Text #2

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.8751. Min Act: -0.0000

Data Index: 1906445 (The Pile)

Max Activating Token Index: 589

Text #3

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.8527. Min Act: 0.0000

Data Index: 1630545 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7984. Min Act: -0.0000

Data Index: 386740 (The Pile)

Max Activating Token Index: 8

Text #5

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7346. Min Act: 0.0000

Data Index: 1251307 (The Pile)

Max Activating Token Index: 869

Text #6

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7819. Min Act: 0.0000

Data Index: 1241751 (The Pile)

Max Activating Token Index: 679

Text #7

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1815722 (The Pile)

Max Activating Token Index: 713

Text #8

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.6791. Min Act: -0.0000

Data Index: 837677 (The Pile)

Max Activating Token Index: 935

Text #9

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7649. Min Act: -0.0000

Data Index: 125350 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7411. Min Act: 0.0000

Data Index: 628432 (The Pile)

Max Activating Token Index: 315

Text #11

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7320. Min Act: -0.0000

Data Index: 394980 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.6011. Min Act: -0.0000

Data Index: 236373 (The Pile)

Max Activating Token Index: 343

Text #13

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7218. Min Act: 0.0000

Data Index: 48574 (The Pile)

Max Activating Token Index: 344

Text #14

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.6934. Min Act: -0.0000

Data Index: 956638 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1654857 (The Pile)

Max Activating Token Index: 240

Text #16

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.6965. Min Act: 0.0001

Data Index: 888046 (The Pile)

Max Activating Token Index: 553

Text #17

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.6767. Min Act: 0.0000

Data Index: 620750 (The Pile)

Max Activating Token Index: 384

Text #18

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.6942. Min Act: -0.0000

Data Index: 1935736 (The Pile)

Max Activating Token Index: 141

Text #19

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1911977 (The Pile)

Max Activating Token Index: 601