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

Dataset: The Pile

Neuron 3973 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1993095 (The Pile)

Max Activating Token Index: 692

Text #1

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.6911. Min Act: -0.0000

Data Index: 225767 (The Pile)

Max Activating Token Index: 610

Text #2

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.7291. Min Act: -0.0000

Data Index: 893967 (The Pile)

Max Activating Token Index: 887

Text #3

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.6760. Min Act: -0.0000

Data Index: 406394 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.7268. Min Act: -0.0000

Data Index: 199024 (The Pile)

Max Activating Token Index: 691

Text #5

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.7187. Min Act: -0.0000

Data Index: 417683 (The Pile)

Max Activating Token Index: 748

Text #6

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1527651 (The Pile)

Max Activating Token Index: 312

Text #7

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.6868. Min Act: -0.0000

Data Index: 406123 (The Pile)

Max Activating Token Index: 190

Text #8

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1417412 (The Pile)

Max Activating Token Index: 163

Text #9

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.6546. Min Act: -0.0000

Data Index: 182244 (The Pile)

Max Activating Token Index: 590

Text #10

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1153622 (The Pile)

Max Activating Token Index: 969

Text #11

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1559786 (The Pile)

Max Activating Token Index: 227

Text #12

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1436520 (The Pile)

Max Activating Token Index: 899

Text #13

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1575378 (The Pile)

Max Activating Token Index: 510

Text #14

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.5681. Min Act: -0.0000

Data Index: 629887 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.5842. Min Act: -0.0000

Data Index: 458879 (The Pile)

Max Activating Token Index: 353

Text #16

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1139676 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.6151. Min Act: -0.0000

Data Index: 707172 (The Pile)

Max Activating Token Index: 263

Text #18

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.5862. Min Act: -0.0000

Data Index: 929896 (The Pile)

Max Activating Token Index: 928

Text #19

Max Range: 0.7291. Min Range: -0.7291

Max Act: 0.5742. Min Act: -0.0000

Data Index: 850416 (The Pile)

Max Activating Token Index: 830