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

Dataset: The Pile

Neuron 3112 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.6997. Min Act: -0.0000

Data Index: 1001378 (The Pile)

Max Activating Token Index: 498

Text #1

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.6463. Min Act: -0.0000

Data Index: 1567265 (The Pile)

Max Activating Token Index: 856

Text #2

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.5304. Min Act: 0.0000

Data Index: 1014093 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.3943. Min Act: -0.0000

Data Index: 29285 (The Pile)

Max Activating Token Index: 585

Text #4

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.4279. Min Act: -0.0000

Data Index: 1143807 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.3779. Min Act: -0.0000

Data Index: 1573879 (The Pile)

Max Activating Token Index: 497

Text #6

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.2833. Min Act: -0.0000

Data Index: 1465863 (The Pile)

Max Activating Token Index: 871

Text #7

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.2569. Min Act: -0.0000

Data Index: 1974942 (The Pile)

Max Activating Token Index: 728

Text #8

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.3161. Min Act: -0.0000

Data Index: 1119110 (The Pile)

Max Activating Token Index: 460

Text #9

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.3015. Min Act: -0.0000

Data Index: 1539430 (The Pile)

Max Activating Token Index: 843

Text #10

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.2195. Min Act: -0.0000

Data Index: 1827114 (The Pile)

Max Activating Token Index: 568

Text #11

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.2926. Min Act: -0.0000

Data Index: 1720551 (The Pile)

Max Activating Token Index: 181

Text #12

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.2199. Min Act: -0.0000

Data Index: 1450378 (The Pile)

Max Activating Token Index: 981

Text #13

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.2675. Min Act: -0.0000

Data Index: 888096 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.1951. Min Act: -0.0000

Data Index: 1026708 (The Pile)

Max Activating Token Index: 641

Text #15

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.1883. Min Act: -0.0000

Data Index: 48460 (The Pile)

Max Activating Token Index: 691

Text #16

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.2594. Min Act: -0.0000

Data Index: 934836 (The Pile)

Max Activating Token Index: 945

Text #17

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.1708. Min Act: -0.0000

Data Index: 1487880 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.2021. Min Act: -0.0000

Data Index: 1210423 (The Pile)

Max Activating Token Index: 492

Text #19

Max Range: 1.6997. Min Range: -1.6997

Max Act: 1.1124. Min Act: -0.0000

Data Index: 563814 (The Pile)

Max Activating Token Index: 707