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

Dataset: The Pile

Neuron 637 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1130373 (The Pile)

Max Activating Token Index: 750

Text #1

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1016156 (The Pile)

Max Activating Token Index: 557

Text #2

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.6262. Min Act: -0.0000

Data Index: 568410 (The Pile)

Max Activating Token Index: 585

Text #3

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5348. Min Act: -0.0000

Data Index: 1570399 (The Pile)

Max Activating Token Index: 685

Text #4

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5900. Min Act: -0.0000

Data Index: 657818 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5795. Min Act: -0.0000

Data Index: 976594 (The Pile)

Max Activating Token Index: 356

Text #6

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5509. Min Act: -0.0000

Data Index: 283319 (The Pile)

Max Activating Token Index: 118

Text #7

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5454. Min Act: -0.0000

Data Index: 592827 (The Pile)

Max Activating Token Index: 951

Text #8

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1476971 (The Pile)

Max Activating Token Index: 492

Text #9

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1902934 (The Pile)

Max Activating Token Index: 450

Text #10

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5350. Min Act: -0.0000

Data Index: 334552 (The Pile)

Max Activating Token Index: 130

Text #11

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5500. Min Act: -0.0000

Data Index: 524301 (The Pile)

Max Activating Token Index: 194

Text #12

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1168338 (The Pile)

Max Activating Token Index: 691

Text #13

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1571226 (The Pile)

Max Activating Token Index: 428

Text #14

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5554. Min Act: -0.0000

Data Index: 155879 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1492037 (The Pile)

Max Activating Token Index: 88

Text #16

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1970832 (The Pile)

Max Activating Token Index: 727

Text #17

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1583672 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5097. Min Act: -0.0000

Data Index: 849983 (The Pile)

Max Activating Token Index: 549

Text #19

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5091. Min Act: -0.0000

Data Index: 879601 (The Pile)

Max Activating Token Index: 467