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

Dataset: The Pile

Neuron 1867 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: 7.3365. Min Range: -7.3365

Max Act: 7.3365. Min Act: -0.0000

Data Index: 257452 (The Pile)

Max Activating Token Index: 478

Text #1

Max Range: 7.3365. Min Range: -7.3365

Max Act: 6.8936. Min Act: -0.0000

Data Index: 1945433 (The Pile)

Max Activating Token Index: 533

Text #2

Max Range: 7.3365. Min Range: -7.3365

Max Act: 6.8896. Min Act: -0.0000

Data Index: 1539714 (The Pile)

Max Activating Token Index: 489

Text #3

Max Range: 7.3365. Min Range: -7.3365

Max Act: 6.8378. Min Act: -0.0000

Data Index: 268522 (The Pile)

Max Activating Token Index: 517

Text #4

Max Range: 7.3365. Min Range: -7.3365

Max Act: 6.9695. Min Act: -0.0000

Data Index: 548844 (The Pile)

Max Activating Token Index: 571

Text #5

Max Range: 7.3365. Min Range: -7.3365

Max Act: 6.8240. Min Act: -0.0000

Data Index: 1899673 (The Pile)

Max Activating Token Index: 861

Text #6

Max Range: 7.3365. Min Range: -7.3365

Max Act: 6.6533. Min Act: -0.0000

Data Index: 965876 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 7.3365. Min Range: -7.3365

Max Act: 6.5990. Min Act: -0.0000

Data Index: 1163721 (The Pile)

Max Activating Token Index: 164

Text #8

Max Range: 7.3365. Min Range: -7.3365

Max Act: 6.6112. Min Act: -0.0000

Data Index: 466342 (The Pile)

Max Activating Token Index: 470

Text #9

Max Range: 7.3365. Min Range: -7.3365

Max Act: 6.5825. Min Act: -0.0000

Data Index: 1518068 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 7.3365. Min Range: -7.3365

Max Act: 6.5284. Min Act: -0.0000

Data Index: 901346 (The Pile)

Max Activating Token Index: 342

Text #11

Max Range: 7.3365. Min Range: -7.3365

Max Act: 6.5282. Min Act: -0.0000

Data Index: 1706807 (The Pile)

Max Activating Token Index: 467

Text #12

Max Range: 7.3365. Min Range: -7.3365

Max Act: 6.2951. Min Act: -0.0000

Data Index: 781573 (The Pile)

Max Activating Token Index: 870

Text #13

Max Range: 7.3365. Min Range: -7.3365

Max Act: 6.5795. Min Act: -0.0000

Data Index: 108667 (The Pile)

Max Activating Token Index: 388

Text #14

Max Range: 7.3365. Min Range: -7.3365

Max Act: 6.0129. Min Act: -0.0000

Data Index: 220824 (The Pile)

Max Activating Token Index: 317

Text #15

Max Range: 7.3365. Min Range: -7.3365

Max Act: 6.1135. Min Act: -0.0000

Data Index: 953824 (The Pile)

Max Activating Token Index: 50

Text #16

Max Range: 7.3365. Min Range: -7.3365

Max Act: 5.7415. Min Act: -0.0000

Data Index: 941931 (The Pile)

Max Activating Token Index: 302

Text #17

Max Range: 7.3365. Min Range: -7.3365

Max Act: 5.9619. Min Act: -0.0000

Data Index: 814026 (The Pile)

Max Activating Token Index: 332

Text #18

Max Range: 7.3365. Min Range: -7.3365

Max Act: 5.8098. Min Act: -0.0000

Data Index: 615722 (The Pile)

Max Activating Token Index: 249

Text #19

Max Range: 7.3365. Min Range: -7.3365

Max Act: 5.7225. Min Act: -0.0000

Data Index: 1979420 (The Pile)

Max Activating Token Index: 229