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

Dataset: The Pile

Neuron 2019 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: 0.8251. Min Range: -0.8251

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1064280 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6792. Min Act: -0.0000

Data Index: 356270 (The Pile)

Max Activating Token Index: 190

Text #2

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1496484 (The Pile)

Max Activating Token Index: 625

Text #3

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1802189 (The Pile)

Max Activating Token Index: 94

Text #4

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1260670 (The Pile)

Max Activating Token Index: 271

Text #5

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1366836 (The Pile)

Max Activating Token Index: 77

Text #6

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7243. Min Act: -0.0000

Data Index: 786124 (The Pile)

Max Activating Token Index: 672

Text #7

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6803. Min Act: -0.0000

Data Index: 190308 (The Pile)

Max Activating Token Index: 436

Text #8

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1020200 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1645308 (The Pile)

Max Activating Token Index: 118

Text #10

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1566645 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.5407. Min Act: -0.0000

Data Index: 950305 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6498. Min Act: -0.0000

Data Index: 285788 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7179. Min Act: -0.0000

Data Index: 712771 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1405998 (The Pile)

Max Activating Token Index: 127

Text #15

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.5226. Min Act: -0.0000

Data Index: 886156 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.5787. Min Act: -0.0000

Data Index: 752489 (The Pile)

Max Activating Token Index: 794

Text #17

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6342. Min Act: -0.0000

Data Index: 1407448 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1882141 (The Pile)

Max Activating Token Index: 199

Text #19

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1364064 (The Pile)

Max Activating Token Index: 342