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

Dataset: The Pile

Neuron 2264 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: 1.7165. Min Range: -1.7165

Max Act: 1.7165. Min Act: -0.0000

Data Index: 237362 (The Pile)

Max Activating Token Index: 469

Text #1

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.5943. Min Act: -0.0000

Data Index: 794681 (The Pile)

Max Activating Token Index: 910

Text #2

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.3768. Min Act: -0.0000

Data Index: 342282 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.2997. Min Act: -0.0000

Data Index: 1449763 (The Pile)

Max Activating Token Index: 147

Text #4

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.0683. Min Act: -0.0000

Data Index: 487572 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.0655. Min Act: -0.0000

Data Index: 1742784 (The Pile)

Max Activating Token Index: 150

Text #6

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.0716. Min Act: -0.0000

Data Index: 1432431 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.8776. Min Act: -0.0000

Data Index: 744514 (The Pile)

Max Activating Token Index: 942

Text #8

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.7785. Min Act: -0.0000

Data Index: 1631874 (The Pile)

Max Activating Token Index: 840

Text #9

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1690842 (The Pile)

Max Activating Token Index: 133

Text #10

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.9215. Min Act: -0.0000

Data Index: 261392 (The Pile)

Max Activating Token Index: 623

Text #11

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.9770. Min Act: -0.0000

Data Index: 902978 (The Pile)

Max Activating Token Index: 842

Text #12

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.9650. Min Act: -0.0000

Data Index: 275300 (The Pile)

Max Activating Token Index: 228

Text #13

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1752577 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.8598. Min Act: -0.0000

Data Index: 1778353 (The Pile)

Max Activating Token Index: 391

Text #15

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.8361. Min Act: -0.0000

Data Index: 419092 (The Pile)

Max Activating Token Index: 87

Text #16

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.8365. Min Act: -0.0000

Data Index: 459623 (The Pile)

Max Activating Token Index: 710

Text #17

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1506462 (The Pile)

Max Activating Token Index: 525

Text #18

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.8563. Min Act: -0.0000

Data Index: 75186 (The Pile)

Max Activating Token Index: 402

Text #19

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.8386. Min Act: -0.0000

Data Index: 175087 (The Pile)

Max Activating Token Index: 826