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

Dataset: The Pile

Neuron 997 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: 1.1667. Min Range: -1.1667

Max Act: 1.1667. Min Act: -0.0000

Data Index: 1650540 (The Pile)

Max Activating Token Index: 3

Text #1

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0754. Min Act: -0.0000

Data Index: 1844737 (The Pile)

Max Activating Token Index: 314

Text #2

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9440. Min Act: -0.0000

Data Index: 369230 (The Pile)

Max Activating Token Index: 670

Text #3

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9770. Min Act: -0.0000

Data Index: 317917 (The Pile)

Max Activating Token Index: 262

Text #4

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9519. Min Act: -0.0000

Data Index: 273698 (The Pile)

Max Activating Token Index: 43

Text #5

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9433. Min Act: -0.0000

Data Index: 962515 (The Pile)

Max Activating Token Index: 306

Text #6

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9050. Min Act: -0.0000

Data Index: 1596575 (The Pile)

Max Activating Token Index: 145

Text #7

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9285. Min Act: -0.0000

Data Index: 11658 (The Pile)

Max Activating Token Index: 498

Text #8

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9181. Min Act: -0.0000

Data Index: 270536 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9268. Min Act: -0.0000

Data Index: 1147183 (The Pile)

Max Activating Token Index: 403

Text #10

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1928924 (The Pile)

Max Activating Token Index: 874

Text #11

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9391. Min Act: -0.0000

Data Index: 62675 (The Pile)

Max Activating Token Index: 496

Text #12

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9337. Min Act: -0.0000

Data Index: 1390377 (The Pile)

Max Activating Token Index: 248

Text #13

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8257. Min Act: -0.0000

Data Index: 261796 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9011. Min Act: -0.0000

Data Index: 1707738 (The Pile)

Max Activating Token Index: 1000

Text #15

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8826. Min Act: -0.0000

Data Index: 1574725 (The Pile)

Max Activating Token Index: 821

Text #16

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8982. Min Act: -0.0000

Data Index: 291892 (The Pile)

Max Activating Token Index: 464

Text #17

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8897. Min Act: -0.0000

Data Index: 1972310 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1478261 (The Pile)

Max Activating Token Index: 834

Text #19

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8155. Min Act: -0.0000

Data Index: 515432 (The Pile)

Max Activating Token Index: 819