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

Dataset: The Pile

Neuron 3162 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: 1.6460. Min Range: -1.6460

Max Act: 1.6460. Min Act: -0.0000

Data Index: 1737297 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.2762. Min Act: -0.0000

Data Index: 79313 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.2768. Min Act: -0.0000

Data Index: 720055 (The Pile)

Max Activating Token Index: 315

Text #3

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.2296. Min Act: -0.0000

Data Index: 74224 (The Pile)

Max Activating Token Index: 60

Text #4

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.2078. Min Act: -0.0000

Data Index: 38037 (The Pile)

Max Activating Token Index: 1019

Text #5

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.2321. Min Act: -0.0000

Data Index: 1862013 (The Pile)

Max Activating Token Index: 757

Text #6

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.2080. Min Act: -0.0000

Data Index: 656243 (The Pile)

Max Activating Token Index: 774

Text #7

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.1937. Min Act: -0.0000

Data Index: 378341 (The Pile)

Max Activating Token Index: 582

Text #8

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.1626. Min Act: -0.0000

Data Index: 1986026 (The Pile)

Max Activating Token Index: 579

Text #9

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.1967. Min Act: -0.0000

Data Index: 9426 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.1995. Min Act: -0.0000

Data Index: 1637679 (The Pile)

Max Activating Token Index: 163

Text #11

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.1174. Min Act: -0.0000

Data Index: 1506747 (The Pile)

Max Activating Token Index: 1005

Text #12

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.1078. Min Act: -0.0000

Data Index: 1109136 (The Pile)

Max Activating Token Index: 343

Text #13

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.1763. Min Act: -0.0000

Data Index: 1264227 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.0666. Min Act: -0.0000

Data Index: 50579 (The Pile)

Max Activating Token Index: 819

Text #15

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.0862. Min Act: -0.0000

Data Index: 1042571 (The Pile)

Max Activating Token Index: 118

Text #16

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.1623. Min Act: -0.0000

Data Index: 1763179 (The Pile)

Max Activating Token Index: 35

Text #17

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.1068. Min Act: -0.0000

Data Index: 875748 (The Pile)

Max Activating Token Index: 632

Text #18

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1924516 (The Pile)

Max Activating Token Index: 813

Text #19

Max Range: 1.6460. Min Range: -1.6460

Max Act: 1.0724. Min Act: -0.0000

Data Index: 1525499 (The Pile)

Max Activating Token Index: 513