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

Dataset: The Pile

Neuron 2572 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1339883 (The Pile)

Max Activating Token Index: 171

Text #1

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1767424 (The Pile)

Max Activating Token Index: 556

Text #2

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1995677 (The Pile)

Max Activating Token Index: 558

Text #3

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 622478 (The Pile)

Max Activating Token Index: 831

Text #4

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 551625 (The Pile)

Max Activating Token Index: 564

Text #5

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1156823 (The Pile)

Max Activating Token Index: 708

Text #6

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1792104 (The Pile)

Max Activating Token Index: 465

Text #7

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1302308 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 211935 (The Pile)

Max Activating Token Index: 670

Text #9

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1754699 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1567554 (The Pile)

Max Activating Token Index: 594

Text #11

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 184989 (The Pile)

Max Activating Token Index: 579

Text #12

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 576627 (The Pile)

Max Activating Token Index: 44

Text #13

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 733274 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 922395 (The Pile)

Max Activating Token Index: 368

Text #15

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 448496 (The Pile)

Max Activating Token Index: 920

Text #16

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1554907 (The Pile)

Max Activating Token Index: 812

Text #17

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 169819 (The Pile)

Max Activating Token Index: 650

Text #18

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 171965 (The Pile)

Max Activating Token Index: 397

Text #19

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 445493 (The Pile)

Max Activating Token Index: 286