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

Dataset: The Pile

Neuron 2361 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: 1.1876. Min Range: -1.1876

Max Act: 1.1618. Min Act: -0.0001

Data Index: 216889 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 1.1876. Min Range: -1.1876

Max Act: 1.1876. Min Act: -0.0000

Data Index: 1846144 (The Pile)

Max Activating Token Index: 677

Text #2

Max Range: 1.1876. Min Range: -1.1876

Max Act: 1.0605. Min Act: -0.0000

Data Index: 640413 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 1.1876. Min Range: -1.1876

Max Act: 1.0309. Min Act: -0.0000

Data Index: 1982523 (The Pile)

Max Activating Token Index: 410

Text #4

Max Range: 1.1876. Min Range: -1.1876

Max Act: 1.0677. Min Act: -0.0000

Data Index: 1523737 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9457. Min Act: -0.0000

Data Index: 316131 (The Pile)

Max Activating Token Index: 990

Text #6

Max Range: 1.1876. Min Range: -1.1876

Max Act: 1.0325. Min Act: -0.0000

Data Index: 1382105 (The Pile)

Max Activating Token Index: 365

Text #7

Max Range: 1.1876. Min Range: -1.1876

Max Act: 1.0254. Min Act: -0.0000

Data Index: 1495623 (The Pile)

Max Activating Token Index: 552

Text #8

Max Range: 1.1876. Min Range: -1.1876

Max Act: 1.0253. Min Act: -0.0000

Data Index: 1796531 (The Pile)

Max Activating Token Index: 853

Text #9

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9850. Min Act: -0.0000

Data Index: 65732 (The Pile)

Max Activating Token Index: 465

Text #10

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9868. Min Act: -0.0000

Data Index: 1867215 (The Pile)

Max Activating Token Index: 752

Text #11

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1421369 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 1.1876. Min Range: -1.1876

Max Act: 1.0266. Min Act: -0.0000

Data Index: 122145 (The Pile)

Max Activating Token Index: 609

Text #13

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1052766 (The Pile)

Max Activating Token Index: 715

Text #14

Max Range: 1.1876. Min Range: -1.1876

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1903830 (The Pile)

Max Activating Token Index: 635

Text #15

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8882. Min Act: -0.0000

Data Index: 437597 (The Pile)

Max Activating Token Index: 101

Text #16

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9672. Min Act: -0.0000

Data Index: 713607 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9279. Min Act: -0.0000

Data Index: 245086 (The Pile)

Max Activating Token Index: 206

Text #18

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.9685. Min Act: -0.0000

Data Index: 921597 (The Pile)

Max Activating Token Index: 569

Text #19

Max Range: 1.1876. Min Range: -1.1876

Max Act: 0.8476. Min Act: -0.0000

Data Index: 607465 (The Pile)

Max Activating Token Index: 145