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

Dataset: The Pile

Neuron 2040 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.7778. Min Act: 0.0000

Data Index: 1729561 (The Pile)

Max Activating Token Index: 300

Text #1

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1919005 (The Pile)

Max Activating Token Index: 181

Text #2

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6335. Min Act: -0.0000

Data Index: 823649 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6088. Min Act: 0.0000

Data Index: 1332469 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1111479 (The Pile)

Max Activating Token Index: 186

Text #5

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6685. Min Act: -0.0000

Data Index: 1669074 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5794. Min Act: -0.0000

Data Index: 679743 (The Pile)

Max Activating Token Index: 727

Text #7

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1382463 (The Pile)

Max Activating Token Index: 975

Text #8

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6115. Min Act: 0.0000

Data Index: 1805958 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1958934 (The Pile)

Max Activating Token Index: 779

Text #10

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5716. Min Act: -0.0000

Data Index: 661039 (The Pile)

Max Activating Token Index: 543

Text #11

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5476. Min Act: -0.0000

Data Index: 393486 (The Pile)

Max Activating Token Index: 277

Text #12

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6018. Min Act: -0.0000

Data Index: 486836 (The Pile)

Max Activating Token Index: 687

Text #13

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5351. Min Act: -0.0000

Data Index: 898363 (The Pile)

Max Activating Token Index: 954

Text #14

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1965241 (The Pile)

Max Activating Token Index: 270

Text #15

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1669622 (The Pile)

Max Activating Token Index: 204

Text #16

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5317. Min Act: -0.0000

Data Index: 841599 (The Pile)

Max Activating Token Index: 444

Text #17

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5332. Min Act: -0.0000

Data Index: 35477 (The Pile)

Max Activating Token Index: 349

Text #18

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1502667 (The Pile)

Max Activating Token Index: 662

Text #19

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5247. Min Act: 0.0000

Data Index: 874967 (The Pile)

Max Activating Token Index: 120