Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4077 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.8294. Min Act: -0.0000

Data Index: 849901 (The Pile)

Max Activating Token Index: 797

Text #1

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.8204. Min Act: -0.0000

Data Index: 1900133 (The Pile)

Max Activating Token Index: 131

Text #2

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.7776. Min Act: -0.0000

Data Index: 1252180 (The Pile)

Max Activating Token Index: 900

Text #3

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.7662. Min Act: -0.0000

Data Index: 1860806 (The Pile)

Max Activating Token Index: 366

Text #4

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.7323. Min Act: -0.0000

Data Index: 458416 (The Pile)

Max Activating Token Index: 665

Text #5

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.7622. Min Act: -0.0000

Data Index: 477902 (The Pile)

Max Activating Token Index: 575

Text #6

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.7369. Min Act: -0.0000

Data Index: 290685 (The Pile)

Max Activating Token Index: 729

Text #7

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1216452 (The Pile)

Max Activating Token Index: 386

Text #8

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6304. Min Act: -0.0000

Data Index: 108014 (The Pile)

Max Activating Token Index: 546

Text #9

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.5960. Min Act: -0.0000

Data Index: 198996 (The Pile)

Max Activating Token Index: 697

Text #10

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1054832 (The Pile)

Max Activating Token Index: 887

Text #11

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6072. Min Act: -0.0000

Data Index: 977139 (The Pile)

Max Activating Token Index: 138

Text #12

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.5703. Min Act: -0.0000

Data Index: 502853 (The Pile)

Max Activating Token Index: 377

Text #13

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1415291 (The Pile)

Max Activating Token Index: 270

Text #14

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.5951. Min Act: -0.0000

Data Index: 1165715 (The Pile)

Max Activating Token Index: 58

Text #15

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1360953 (The Pile)

Max Activating Token Index: 627

Text #16

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.5627. Min Act: -0.0000

Data Index: 970079 (The Pile)

Max Activating Token Index: 46

Text #17

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.5472. Min Act: -0.0000

Data Index: 145537 (The Pile)

Max Activating Token Index: 879

Text #18

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.5754. Min Act: -0.0000

Data Index: 830913 (The Pile)

Max Activating Token Index: 923

Text #19

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.5680. Min Act: -0.0000

Data Index: 1877658 (The Pile)

Max Activating Token Index: 85