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

Dataset: The Pile

Neuron 764 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2448. Min Range: -1.2448

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1756371 (The Pile)

Max Activating Token Index: 582

Text #1

Max Range: 1.2448. Min Range: -1.2448

Max Act: 1.1500. Min Act: -0.0000

Data Index: 816893 (The Pile)

Max Activating Token Index: 396

Text #2

Max Range: 1.2448. Min Range: -1.2448

Max Act: 1.0684. Min Act: -0.0000

Data Index: 402446 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.9393. Min Act: -0.0000

Data Index: 82761 (The Pile)

Max Activating Token Index: 373

Text #4

Max Range: 1.2448. Min Range: -1.2448

Max Act: 1.1972. Min Act: -0.0000

Data Index: 1827140 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 1.2448. Min Range: -1.2448

Max Act: 1.0360. Min Act: -0.0000

Data Index: 315480 (The Pile)

Max Activating Token Index: 800

Text #6

Max Range: 1.2448. Min Range: -1.2448

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1125118 (The Pile)

Max Activating Token Index: 340

Text #7

Max Range: 1.2448. Min Range: -1.2448

Max Act: 1.0297. Min Act: -0.0000

Data Index: 1616290 (The Pile)

Max Activating Token Index: 238

Text #8

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.9960. Min Act: -0.0000

Data Index: 552226 (The Pile)

Max Activating Token Index: 174

Text #9

Max Range: 1.2448. Min Range: -1.2448

Max Act: 1.0356. Min Act: -0.0000

Data Index: 1619674 (The Pile)

Max Activating Token Index: 176

Text #10

Max Range: 1.2448. Min Range: -1.2448

Max Act: 1.2448. Min Act: -0.0000

Data Index: 451715 (The Pile)

Max Activating Token Index: 174

Text #11

Max Range: 1.2448. Min Range: -1.2448

Max Act: 1.0133. Min Act: -0.0000

Data Index: 1747171 (The Pile)

Max Activating Token Index: 424

Text #12

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1253433 (The Pile)

Max Activating Token Index: 641

Text #13

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.9501. Min Act: -0.0000

Data Index: 340267 (The Pile)

Max Activating Token Index: 453

Text #14

Max Range: 1.2448. Min Range: -1.2448

Max Act: 1.0644. Min Act: -0.0000

Data Index: 1073149 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.9327. Min Act: -0.0000

Data Index: 68955 (The Pile)

Max Activating Token Index: 228

Text #16

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.9631. Min Act: -0.0000

Data Index: 836049 (The Pile)

Max Activating Token Index: 781

Text #17

Max Range: 1.2448. Min Range: -1.2448

Max Act: 1.0668. Min Act: -0.0000

Data Index: 1633385 (The Pile)

Max Activating Token Index: 350

Text #18

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.9987. Min Act: -0.0000

Data Index: 1984039 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.8936. Min Act: -0.0000

Data Index: 1814891 (The Pile)

Max Activating Token Index: 238