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

Dataset: The Pile

Neuron 1924 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: 1.6783. Min Range: -1.6783

Max Act: 1.6783. Min Act: -0.0000

Data Index: 1974657 (The Pile)

Max Activating Token Index: 876

Text #1

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.6566. Min Act: -0.0000

Data Index: 1448629 (The Pile)

Max Activating Token Index: 461

Text #2

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5582. Min Act: -0.0000

Data Index: 510924 (The Pile)

Max Activating Token Index: 130

Text #3

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5164. Min Act: -0.0000

Data Index: 457264 (The Pile)

Max Activating Token Index: 106

Text #4

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.3228. Min Act: -0.0000

Data Index: 298595 (The Pile)

Max Activating Token Index: 97

Text #5

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.3737. Min Act: -0.0000

Data Index: 1187971 (The Pile)

Max Activating Token Index: 439

Text #6

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.4840. Min Act: -0.0000

Data Index: 859968 (The Pile)

Max Activating Token Index: 663

Text #7

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.2576. Min Act: -0.0000

Data Index: 118615 (The Pile)

Max Activating Token Index: 249

Text #8

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.2011. Min Act: -0.0000

Data Index: 112035 (The Pile)

Max Activating Token Index: 77

Text #9

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.1715. Min Act: -0.0000

Data Index: 202784 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.1747. Min Act: -0.0000

Data Index: 1216584 (The Pile)

Max Activating Token Index: 57

Text #11

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.2358. Min Act: -0.0000

Data Index: 1913478 (The Pile)

Max Activating Token Index: 916

Text #12

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.2238. Min Act: -0.0000

Data Index: 599713 (The Pile)

Max Activating Token Index: 522

Text #13

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.2004. Min Act: -0.0000

Data Index: 313720 (The Pile)

Max Activating Token Index: 615

Text #14

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.0781. Min Act: -0.0000

Data Index: 1822814 (The Pile)

Max Activating Token Index: 191

Text #15

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.1319. Min Act: -0.0000

Data Index: 428117 (The Pile)

Max Activating Token Index: 512

Text #16

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.1420. Min Act: -0.0000

Data Index: 1392466 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.1169. Min Act: -0.0000

Data Index: 632535 (The Pile)

Max Activating Token Index: 250

Text #18

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.1755. Min Act: -0.0000

Data Index: 335990 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 1.6783. Min Range: -1.6783

Max Act: 0.9873. Min Act: -0.0000

Data Index: 1809614 (The Pile)

Max Activating Token Index: 873