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

Dataset: The Pile

Neuron 2618 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: 1.7499. Min Range: -1.7499

Max Act: 1.7499. Min Act: -0.0000

Data Index: 104161 (The Pile)

Max Activating Token Index: 834

Text #1

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.4598. Min Act: -0.0000

Data Index: 1815063 (The Pile)

Max Activating Token Index: 229

Text #2

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.4825. Min Act: -0.0000

Data Index: 257572 (The Pile)

Max Activating Token Index: 264

Text #3

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.2733. Min Act: -0.0000

Data Index: 970497 (The Pile)

Max Activating Token Index: 1016

Text #4

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.1771. Min Act: 0.0000

Data Index: 577352 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 1.7499. Min Range: -1.7499

Max Act: 0.9699. Min Act: -0.0000

Data Index: 1672806 (The Pile)

Max Activating Token Index: 231

Text #6

Max Range: 1.7499. Min Range: -1.7499

Max Act: 1.0446. Min Act: 0.0001

Data Index: 347295 (The Pile)

Max Activating Token Index: 837

Text #7

Max Range: 1.7499. Min Range: -1.7499

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1343028 (The Pile)

Max Activating Token Index: 771

Text #8

Max Range: 1.7499. Min Range: -1.7499

Max Act: 0.9497. Min Act: -0.0000

Data Index: 227243 (The Pile)

Max Activating Token Index: 802

Text #9

Max Range: 1.7499. Min Range: -1.7499

Max Act: 0.8751. Min Act: -0.0000

Data Index: 694894 (The Pile)

Max Activating Token Index: 976

Text #10

Max Range: 1.7499. Min Range: -1.7499

Max Act: 0.9120. Min Act: 0.0000

Data Index: 805307 (The Pile)

Max Activating Token Index: 882

Text #11

Max Range: 1.7499. Min Range: -1.7499

Max Act: 0.7852. Min Act: -0.0000

Data Index: 1045768 (The Pile)

Max Activating Token Index: 812

Text #12

Max Range: 1.7499. Min Range: -1.7499

Max Act: 0.8451. Min Act: -0.0000

Data Index: 728244 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 1.7499. Min Range: -1.7499

Max Act: 0.8170. Min Act: 0.0001

Data Index: 1821228 (The Pile)

Max Activating Token Index: 973

Text #14

Max Range: 1.7499. Min Range: -1.7499

Max Act: 0.8640. Min Act: -0.0000

Data Index: 1549883 (The Pile)

Max Activating Token Index: 442

Text #15

Max Range: 1.7499. Min Range: -1.7499

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1998900 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 1.7499. Min Range: -1.7499

Max Act: 0.8223. Min Act: -0.0000

Data Index: 831880 (The Pile)

Max Activating Token Index: 797

Text #17

Max Range: 1.7499. Min Range: -1.7499

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1398831 (The Pile)

Max Activating Token Index: 505

Text #18

Max Range: 1.7499. Min Range: -1.7499

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1727527 (The Pile)

Max Activating Token Index: 241

Text #19

Max Range: 1.7499. Min Range: -1.7499

Max Act: 0.7823. Min Act: 0.0000

Data Index: 1382955 (The Pile)

Max Activating Token Index: 161