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

Dataset: The Pile

Neuron 4389 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.9998. Min Act: -0.0000

Data Index: 1391187 (The Pile)

Max Activating Token Index: 858

Text #1

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1944961 (The Pile)

Max Activating Token Index: 449

Text #2

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1008435 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7368. Min Act: -0.0000

Data Index: 837002 (The Pile)

Max Activating Token Index: 35

Text #4

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7008. Min Act: -0.0000

Data Index: 1561678 (The Pile)

Max Activating Token Index: 369

Text #5

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6931. Min Act: -0.0000

Data Index: 1278283 (The Pile)

Max Activating Token Index: 410

Text #6

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6685. Min Act: -0.0000

Data Index: 184108 (The Pile)

Max Activating Token Index: 1020

Text #7

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6120. Min Act: -0.0000

Data Index: 388806 (The Pile)

Max Activating Token Index: 721

Text #8

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1355570 (The Pile)

Max Activating Token Index: 966

Text #9

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1147107 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6821. Min Act: -0.0000

Data Index: 529764 (The Pile)

Max Activating Token Index: 464

Text #11

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6495. Min Act: -0.0000

Data Index: 595326 (The Pile)

Max Activating Token Index: 938

Text #12

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6508. Min Act: -0.0000

Data Index: 1652840 (The Pile)

Max Activating Token Index: 99

Text #13

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6619. Min Act: -0.0000

Data Index: 1079189 (The Pile)

Max Activating Token Index: 640

Text #14

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6656. Min Act: -0.0000

Data Index: 809590 (The Pile)

Max Activating Token Index: 418

Text #15

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6416. Min Act: -0.0000

Data Index: 151535 (The Pile)

Max Activating Token Index: 215

Text #16

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6407. Min Act: -0.0000

Data Index: 117892 (The Pile)

Max Activating Token Index: 490

Text #17

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.5815. Min Act: -0.0000

Data Index: 1618331 (The Pile)

Max Activating Token Index: 791

Text #18

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1810600 (The Pile)

Max Activating Token Index: 836

Text #19

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6157. Min Act: -0.0000

Data Index: 266547 (The Pile)

Max Activating Token Index: 645