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

Dataset: The Pile

Neuron 3008 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1993187 (The Pile)

Max Activating Token Index: 865

Text #1

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.9649. Min Act: -0.0000

Data Index: 983302 (The Pile)

Max Activating Token Index: 730

Text #2

Max Range: 1.0265. Min Range: -1.0265

Max Act: 1.0265. Min Act: -0.0000

Data Index: 1890321 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1562716 (The Pile)

Max Activating Token Index: 343

Text #4

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7810. Min Act: -0.0000

Data Index: 233352 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1362790 (The Pile)

Max Activating Token Index: 987

Text #6

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8015. Min Act: -0.0000

Data Index: 177186 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8565. Min Act: -0.0000

Data Index: 1586302 (The Pile)

Max Activating Token Index: 578

Text #8

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1983981 (The Pile)

Max Activating Token Index: 125

Text #9

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8146. Min Act: -0.0000

Data Index: 1393475 (The Pile)

Max Activating Token Index: 617

Text #10

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7647. Min Act: -0.0000

Data Index: 523500 (The Pile)

Max Activating Token Index: 854

Text #11

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8290. Min Act: -0.0000

Data Index: 488697 (The Pile)

Max Activating Token Index: 465

Text #12

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8591. Min Act: -0.0000

Data Index: 1136523 (The Pile)

Max Activating Token Index: 98

Text #13

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8187. Min Act: -0.0000

Data Index: 1063782 (The Pile)

Max Activating Token Index: 709

Text #14

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1050873 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1607994 (The Pile)

Max Activating Token Index: 837

Text #16

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7702. Min Act: -0.0000

Data Index: 425188 (The Pile)

Max Activating Token Index: 482

Text #17

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7601. Min Act: -0.0000

Data Index: 1985663 (The Pile)

Max Activating Token Index: 975

Text #18

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1673135 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1665396 (The Pile)

Max Activating Token Index: 792