Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1972 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1460298 (The Pile)

Max Activating Token Index: 116

Text #1

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1771779 (The Pile)

Max Activating Token Index: 291

Text #2

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4666. Min Act: -0.0000

Data Index: 207875 (The Pile)

Max Activating Token Index: 805

Text #3

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4636. Min Act: -0.0000

Data Index: 677529 (The Pile)

Max Activating Token Index: 728

Text #4

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1690699 (The Pile)

Max Activating Token Index: 267

Text #5

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4825. Min Act: -0.0000

Data Index: 611333 (The Pile)

Max Activating Token Index: 849

Text #6

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1608763 (The Pile)

Max Activating Token Index: 535

Text #7

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4815. Min Act: -0.0000

Data Index: 753849 (The Pile)

Max Activating Token Index: 404

Text #8

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1356152 (The Pile)

Max Activating Token Index: 177

Text #9

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4639. Min Act: -0.0000

Data Index: 794652 (The Pile)

Max Activating Token Index: 58

Text #10

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1894529 (The Pile)

Max Activating Token Index: 916

Text #11

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4520. Min Act: -0.0000

Data Index: 583303 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1809370 (The Pile)

Max Activating Token Index: 972

Text #13

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1618891 (The Pile)

Max Activating Token Index: 755

Text #14

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4428. Min Act: -0.0000

Data Index: 609301 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1150465 (The Pile)

Max Activating Token Index: 579

Text #16

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4042. Min Act: -0.0000

Data Index: 1370690 (The Pile)

Max Activating Token Index: 927

Text #17

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4286. Min Act: -0.0000

Data Index: 1172682 (The Pile)

Max Activating Token Index: 718

Text #18

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4377. Min Act: -0.0000

Data Index: 342418 (The Pile)

Max Activating Token Index: 203

Text #19

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4096. Min Act: -0.0000

Data Index: 771894 (The Pile)

Max Activating Token Index: 72