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

Dataset: The Pile

Neuron 1993 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: 0.7432. Min Range: -0.7432

Max Act: 0.7432. Min Act: -0.0000

Data Index: 813558 (The Pile)

Max Activating Token Index: 378

Text #1

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1399261 (The Pile)

Max Activating Token Index: 785

Text #2

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6113. Min Act: -0.0000

Data Index: 870814 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6080. Min Act: -0.0000

Data Index: 1544500 (The Pile)

Max Activating Token Index: 513

Text #4

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5990. Min Act: -0.0000

Data Index: 621843 (The Pile)

Max Activating Token Index: 349

Text #5

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5992. Min Act: -0.0000

Data Index: 220183 (The Pile)

Max Activating Token Index: 652

Text #6

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5539. Min Act: -0.0000

Data Index: 235079 (The Pile)

Max Activating Token Index: 950

Text #7

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1798322 (The Pile)

Max Activating Token Index: 857

Text #8

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5516. Min Act: -0.0000

Data Index: 828960 (The Pile)

Max Activating Token Index: 241

Text #9

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.4805. Min Act: -0.0000

Data Index: 557803 (The Pile)

Max Activating Token Index: 579

Text #10

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1073037 (The Pile)

Max Activating Token Index: 750

Text #11

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1272561 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5518. Min Act: -0.0000

Data Index: 828549 (The Pile)

Max Activating Token Index: 683

Text #13

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.4457. Min Act: -0.0000

Data Index: 148857 (The Pile)

Max Activating Token Index: 820

Text #14

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1002192 (The Pile)

Max Activating Token Index: 992

Text #15

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5155. Min Act: 0.0000

Data Index: 1292313 (The Pile)

Max Activating Token Index: 560

Text #16

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5210. Min Act: -0.0000

Data Index: 1586152 (The Pile)

Max Activating Token Index: 593

Text #17

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1620922 (The Pile)

Max Activating Token Index: 924

Text #18

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.4941. Min Act: -0.0000

Data Index: 699511 (The Pile)

Max Activating Token Index: 1006

Text #19

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1102213 (The Pile)

Max Activating Token Index: 835