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

Dataset: The Pile

Neuron 1701 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 13.6059. Min Range: -13.6059

Max Act: 13.6003. Min Act: -0.0000

Data Index: 1443596 (The Pile)

Max Activating Token Index: 797

Text #1

Max Range: 13.6059. Min Range: -13.6059

Max Act: 13.6059. Min Act: -0.0000

Data Index: 869031 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 13.6059. Min Range: -13.6059

Max Act: 13.6039. Min Act: -0.0000

Data Index: 1687798 (The Pile)

Max Activating Token Index: 985

Text #3

Max Range: 13.6059. Min Range: -13.6059

Max Act: 13.5349. Min Act: -0.0000

Data Index: 189677 (The Pile)

Max Activating Token Index: 669

Text #4

Max Range: 13.6059. Min Range: -13.6059

Max Act: 13.1858. Min Act: -0.0000

Data Index: 110056 (The Pile)

Max Activating Token Index: 964

Text #5

Max Range: 13.6059. Min Range: -13.6059

Max Act: 13.0130. Min Act: -0.0000

Data Index: 5598 (The Pile)

Max Activating Token Index: 648

Text #6

Max Range: 13.6059. Min Range: -13.6059

Max Act: 13.0985. Min Act: -0.0001

Data Index: 611788 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 13.6059. Min Range: -13.6059

Max Act: 13.1718. Min Act: -0.0000

Data Index: 1900181 (The Pile)

Max Activating Token Index: 930

Text #8

Max Range: 13.6059. Min Range: -13.6059

Max Act: 12.8678. Min Act: -0.0000

Data Index: 861721 (The Pile)

Max Activating Token Index: 660

Text #9

Max Range: 13.6059. Min Range: -13.6059

Max Act: 13.2537. Min Act: -0.0000

Data Index: 1228327 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 13.6059. Min Range: -13.6059

Max Act: 12.9498. Min Act: -0.0000

Data Index: 468066 (The Pile)

Max Activating Token Index: 473

Text #11

Max Range: 13.6059. Min Range: -13.6059

Max Act: 12.8659. Min Act: -0.0000

Data Index: 1176773 (The Pile)

Max Activating Token Index: 406

Text #12

Max Range: 13.6059. Min Range: -13.6059

Max Act: 12.7802. Min Act: -0.0000

Data Index: 1051215 (The Pile)

Max Activating Token Index: 133

Text #13

Max Range: 13.6059. Min Range: -13.6059

Max Act: 12.7406. Min Act: -0.0000

Data Index: 1436978 (The Pile)

Max Activating Token Index: 774

Text #14

Max Range: 13.6059. Min Range: -13.6059

Max Act: 12.5541. Min Act: -0.0000

Data Index: 621042 (The Pile)

Max Activating Token Index: 208

Text #15

Max Range: 13.6059. Min Range: -13.6059

Max Act: 12.6243. Min Act: -0.0000

Data Index: 167055 (The Pile)

Max Activating Token Index: 273

Text #16

Max Range: 13.6059. Min Range: -13.6059

Max Act: 12.4229. Min Act: -0.0001

Data Index: 1185561 (The Pile)

Max Activating Token Index: 348

Text #17

Max Range: 13.6059. Min Range: -13.6059

Max Act: 12.5771. Min Act: -0.0000

Data Index: 1228628 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 13.6059. Min Range: -13.6059

Max Act: 12.4483. Min Act: -0.0000

Data Index: 1198552 (The Pile)

Max Activating Token Index: 876

Text #19

Max Range: 13.6059. Min Range: -13.6059

Max Act: 12.1194. Min Act: -0.0000

Data Index: 1584123 (The Pile)

Max Activating Token Index: 280