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

Dataset: The Pile

Neuron 1885 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: 0.7228. Min Range: -0.7228

Max Act: 0.7228. Min Act: -0.0000

Data Index: 204708 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.7154. Min Act: -0.0000

Data Index: 662790 (The Pile)

Max Activating Token Index: 402

Text #2

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1664607 (The Pile)

Max Activating Token Index: 638

Text #3

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1832369 (The Pile)

Max Activating Token Index: 90

Text #4

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1843492 (The Pile)

Max Activating Token Index: 114

Text #5

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.6824. Min Act: -0.0000

Data Index: 629135 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1084840 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1424284 (The Pile)

Max Activating Token Index: 66

Text #8

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.5768. Min Act: -0.0000

Data Index: 1907266 (The Pile)

Max Activating Token Index: 10

Text #9

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1027791 (The Pile)

Max Activating Token Index: 326

Text #10

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1808012 (The Pile)

Max Activating Token Index: 321

Text #11

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1131363 (The Pile)

Max Activating Token Index: 911

Text #12

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.5900. Min Act: -0.0000

Data Index: 928021 (The Pile)

Max Activating Token Index: 628

Text #13

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.5298. Min Act: -0.0000

Data Index: 401291 (The Pile)

Max Activating Token Index: 460

Text #14

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.5405. Min Act: -0.0000

Data Index: 206336 (The Pile)

Max Activating Token Index: 991

Text #15

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.5568. Min Act: -0.0000

Data Index: 397404 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.4890. Min Act: -0.0000

Data Index: 759543 (The Pile)

Max Activating Token Index: 230

Text #17

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1878895 (The Pile)

Max Activating Token Index: 659

Text #18

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1646321 (The Pile)

Max Activating Token Index: 781

Text #19

Max Range: 0.7228. Min Range: -0.7228

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1088409 (The Pile)

Max Activating Token Index: 406