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

Dataset: The Pile

Neuron 4848 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: 0.5705. Min Range: -0.5705

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1897002 (The Pile)

Max Activating Token Index: 704

Text #1

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1894090 (The Pile)

Max Activating Token Index: 513

Text #2

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1983455 (The Pile)

Max Activating Token Index: 737

Text #3

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5469. Min Act: -0.0000

Data Index: 379361 (The Pile)

Max Activating Token Index: 205

Text #4

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5445. Min Act: -0.0000

Data Index: 582298 (The Pile)

Max Activating Token Index: 465

Text #5

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5407. Min Act: -0.0000

Data Index: 557754 (The Pile)

Max Activating Token Index: 448

Text #6

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5705. Min Act: -0.0000

Data Index: 1039601 (The Pile)

Max Activating Token Index: 96

Text #7

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5376. Min Act: -0.0000

Data Index: 651163 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4619. Min Act: -0.0000

Data Index: 1797744 (The Pile)

Max Activating Token Index: 559

Text #9

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4459. Min Act: -0.0001

Data Index: 1315751 (The Pile)

Max Activating Token Index: 520

Text #10

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1948792 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4594. Min Act: -0.0000

Data Index: 618259 (The Pile)

Max Activating Token Index: 186

Text #12

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1655693 (The Pile)

Max Activating Token Index: 392

Text #13

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1469284 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1793251 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1785110 (The Pile)

Max Activating Token Index: 982

Text #16

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1341202 (The Pile)

Max Activating Token Index: 677

Text #17

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1935098 (The Pile)

Max Activating Token Index: 723

Text #18

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1019801 (The Pile)

Max Activating Token Index: 371

Text #19

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4353. Min Act: -0.0000

Data Index: 831409 (The Pile)

Max Activating Token Index: 639