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

Dataset: The Pile

Neuron 2561 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: 0.8774. Min Range: -0.8774

Max Act: 0.8774. Min Act: -0.0000

Data Index: 290023 (The Pile)

Max Activating Token Index: 74

Text #1

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.8130. Min Act: -0.0000

Data Index: 606632 (The Pile)

Max Activating Token Index: 649

Text #2

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1386358 (The Pile)

Max Activating Token Index: 738

Text #3

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1633602 (The Pile)

Max Activating Token Index: 428

Text #4

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7251. Min Act: -0.0000

Data Index: 985409 (The Pile)

Max Activating Token Index: 217

Text #5

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6861. Min Act: -0.0000

Data Index: 159100 (The Pile)

Max Activating Token Index: 495

Text #6

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7112. Min Act: -0.0000

Data Index: 1436890 (The Pile)

Max Activating Token Index: 151

Text #7

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1895382 (The Pile)

Max Activating Token Index: 959

Text #8

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6712. Min Act: -0.0000

Data Index: 384377 (The Pile)

Max Activating Token Index: 302

Text #9

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1948661 (The Pile)

Max Activating Token Index: 535

Text #10

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1053346 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.5982. Min Act: -0.0000

Data Index: 435902 (The Pile)

Max Activating Token Index: 607

Text #12

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6695. Min Act: -0.0000

Data Index: 173952 (The Pile)

Max Activating Token Index: 180

Text #13

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1398764 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6353. Min Act: -0.0000

Data Index: 330219 (The Pile)

Max Activating Token Index: 548

Text #15

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6538. Min Act: -0.0000

Data Index: 114240 (The Pile)

Max Activating Token Index: 198

Text #16

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1337623 (The Pile)

Max Activating Token Index: 808

Text #17

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6496. Min Act: -0.0000

Data Index: 838106 (The Pile)

Max Activating Token Index: 1004

Text #18

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1594204 (The Pile)

Max Activating Token Index: 595

Text #19

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1343275 (The Pile)

Max Activating Token Index: 972