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

Dataset: The Pile

Neuron 1816 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: 1.5241. Min Range: -1.5241

Max Act: 1.5241. Min Act: -0.0000

Data Index: 1248580 (The Pile)

Max Activating Token Index: 235

Text #1

Max Range: 1.5241. Min Range: -1.5241

Max Act: 1.4554. Min Act: -0.0000

Data Index: 412798 (The Pile)

Max Activating Token Index: 77

Text #2

Max Range: 1.5241. Min Range: -1.5241

Max Act: 1.2067. Min Act: 0.0000

Data Index: 1200510 (The Pile)

Max Activating Token Index: 822

Text #3

Max Range: 1.5241. Min Range: -1.5241

Max Act: 1.2063. Min Act: -0.0000

Data Index: 176816 (The Pile)

Max Activating Token Index: 836

Text #4

Max Range: 1.5241. Min Range: -1.5241

Max Act: 1.1038. Min Act: -0.0000

Data Index: 529382 (The Pile)

Max Activating Token Index: 646

Text #5

Max Range: 1.5241. Min Range: -1.5241

Max Act: 1.1504. Min Act: -0.0000

Data Index: 310852 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 1.5241. Min Range: -1.5241

Max Act: 1.0944. Min Act: -0.0000

Data Index: 1793303 (The Pile)

Max Activating Token Index: 1020

Text #7

Max Range: 1.5241. Min Range: -1.5241

Max Act: 1.0842. Min Act: -0.0000

Data Index: 454042 (The Pile)

Max Activating Token Index: 922

Text #8

Max Range: 1.5241. Min Range: -1.5241

Max Act: 1.0648. Min Act: -0.0000

Data Index: 1128886 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 1.5241. Min Range: -1.5241

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1937762 (The Pile)

Max Activating Token Index: 124

Text #10

Max Range: 1.5241. Min Range: -1.5241

Max Act: 1.0245. Min Act: -0.0000

Data Index: 914595 (The Pile)

Max Activating Token Index: 411

Text #11

Max Range: 1.5241. Min Range: -1.5241

Max Act: 0.9869. Min Act: 0.0000

Data Index: 857133 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 1.5241. Min Range: -1.5241

Max Act: 0.9267. Min Act: -0.0000

Data Index: 447787 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 1.5241. Min Range: -1.5241

Max Act: 0.9525. Min Act: 0.0000

Data Index: 870000 (The Pile)

Max Activating Token Index: 265

Text #14

Max Range: 1.5241. Min Range: -1.5241

Max Act: 0.8958. Min Act: -0.0000

Data Index: 953141 (The Pile)

Max Activating Token Index: 881

Text #15

Max Range: 1.5241. Min Range: -1.5241

Max Act: 0.9428. Min Act: -0.0000

Data Index: 1921362 (The Pile)

Max Activating Token Index: 674

Text #16

Max Range: 1.5241. Min Range: -1.5241

Max Act: 0.9615. Min Act: 0.0000

Data Index: 593024 (The Pile)

Max Activating Token Index: 806

Text #17

Max Range: 1.5241. Min Range: -1.5241

Max Act: 0.9315. Min Act: -0.0000

Data Index: 1277765 (The Pile)

Max Activating Token Index: 840

Text #18

Max Range: 1.5241. Min Range: -1.5241

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1727393 (The Pile)

Max Activating Token Index: 726

Text #19

Max Range: 1.5241. Min Range: -1.5241

Max Act: 0.9041. Min Act: -0.0000

Data Index: 358002 (The Pile)

Max Activating Token Index: 258