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

Dataset: The Pile

Neuron 1861 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: 0.7580. Min Range: -0.7580

Max Act: 0.5948. Min Act: -0.0000

Data Index: 887259 (The Pile)

Max Activating Token Index: 919

Text #1

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1776174 (The Pile)

Max Activating Token Index: 872

Text #2

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1819717 (The Pile)

Max Activating Token Index: 419

Text #3

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.7211. Min Act: -0.0000

Data Index: 1419323 (The Pile)

Max Activating Token Index: 637

Text #4

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1327885 (The Pile)

Max Activating Token Index: 950

Text #5

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1289055 (The Pile)

Max Activating Token Index: 813

Text #6

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6390. Min Act: -0.0000

Data Index: 345957 (The Pile)

Max Activating Token Index: 530

Text #7

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.7338. Min Act: -0.0000

Data Index: 546555 (The Pile)

Max Activating Token Index: 678

Text #8

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1266134 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6176. Min Act: -0.0000

Data Index: 722445 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1000578 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5307. Min Act: -0.0000

Data Index: 977879 (The Pile)

Max Activating Token Index: 833

Text #12

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5680. Min Act: -0.0000

Data Index: 594184 (The Pile)

Max Activating Token Index: 212

Text #13

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5005. Min Act: -0.0000

Data Index: 1724966 (The Pile)

Max Activating Token Index: 741

Text #14

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1941915 (The Pile)

Max Activating Token Index: 448

Text #15

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1173762 (The Pile)

Max Activating Token Index: 739

Text #16

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5057. Min Act: -0.0000

Data Index: 596920 (The Pile)

Max Activating Token Index: 955

Text #17

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1626810 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.4901. Min Act: -0.0000

Data Index: 65784 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.4633. Min Act: -0.0000

Data Index: 745655 (The Pile)

Max Activating Token Index: 711