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

Dataset: The Pile

Neuron 892 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3545. Min Act: -0.0000

Data Index: 562854 (The Pile)

Max Activating Token Index: 979

Text #1

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3445. Min Act: -0.0000

Data Index: 1938559 (The Pile)

Max Activating Token Index: 748

Text #2

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.2982. Min Act: -0.0000

Data Index: 727149 (The Pile)

Max Activating Token Index: 802

Text #3

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3145. Min Act: -0.0000

Data Index: 1465558 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.2306. Min Act: -0.0000

Data Index: 340178 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3204. Min Act: -0.0000

Data Index: 1159760 (The Pile)

Max Activating Token Index: 450

Text #6

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1791. Min Act: -0.0000

Data Index: 732312 (The Pile)

Max Activating Token Index: 854

Text #7

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1396. Min Act: -0.0000

Data Index: 147321 (The Pile)

Max Activating Token Index: 131

Text #8

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1301. Min Act: -0.0000

Data Index: 946278 (The Pile)

Max Activating Token Index: 1004

Text #9

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1578. Min Act: -0.0000

Data Index: 622776 (The Pile)

Max Activating Token Index: 986

Text #10

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1221. Min Act: -0.0000

Data Index: 1540595 (The Pile)

Max Activating Token Index: 913

Text #11

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1036. Min Act: -0.0000

Data Index: 861209 (The Pile)

Max Activating Token Index: 627

Text #12

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.0381. Min Act: -0.0000

Data Index: 1237280 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.0876. Min Act: -0.0000

Data Index: 1326748 (The Pile)

Max Activating Token Index: 800

Text #14

Max Range: 1.3545. Min Range: -1.3545

Max Act: 0.9798. Min Act: -0.0000

Data Index: 371927 (The Pile)

Max Activating Token Index: 642

Text #15

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1653. Min Act: -0.0000

Data Index: 1196165 (The Pile)

Max Activating Token Index: 591

Text #16

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.0722. Min Act: -0.0000

Data Index: 103037 (The Pile)

Max Activating Token Index: 851

Text #17

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.0032. Min Act: -0.0000

Data Index: 747409 (The Pile)

Max Activating Token Index: 942

Text #18

Max Range: 1.3545. Min Range: -1.3545

Max Act: 0.9900. Min Act: -0.0000

Data Index: 493910 (The Pile)

Max Activating Token Index: 787

Text #19

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.0109. Min Act: -0.0000

Data Index: 1259528 (The Pile)

Max Activating Token Index: 248