Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2409 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.6834. Min Act: -0.0000

Data Index: 133031 (The Pile)

Max Activating Token Index: 664

Text #1

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.3571. Min Act: -0.0000

Data Index: 1329427 (The Pile)

Max Activating Token Index: 790

Text #2

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.2781. Min Act: -0.0000

Data Index: 493233 (The Pile)

Max Activating Token Index: 153

Text #3

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.1729. Min Act: -0.0000

Data Index: 695349 (The Pile)

Max Activating Token Index: 778

Text #4

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.1110. Min Act: -0.0000

Data Index: 1629689 (The Pile)

Max Activating Token Index: 688

Text #5

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.1766. Min Act: -0.0000

Data Index: 1867303 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 1.6834. Min Range: -1.6834

Max Act: 1.1355. Min Act: -0.0000

Data Index: 665525 (The Pile)

Max Activating Token Index: 504

Text #7

Max Range: 1.6834. Min Range: -1.6834

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1220005 (The Pile)

Max Activating Token Index: 759

Text #8

Max Range: 1.6834. Min Range: -1.6834

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1757694 (The Pile)

Max Activating Token Index: 299

Text #9

Max Range: 1.6834. Min Range: -1.6834

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1031417 (The Pile)

Max Activating Token Index: 328

Text #10

Max Range: 1.6834. Min Range: -1.6834

Max Act: 0.9574. Min Act: -0.0000

Data Index: 1619135 (The Pile)

Max Activating Token Index: 345

Text #11

Max Range: 1.6834. Min Range: -1.6834

Max Act: 0.9455. Min Act: -0.0000

Data Index: 1466130 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 1.6834. Min Range: -1.6834

Max Act: 0.9454. Min Act: -0.0000

Data Index: 1041996 (The Pile)

Max Activating Token Index: 521

Text #13

Max Range: 1.6834. Min Range: -1.6834

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1177125 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 1.6834. Min Range: -1.6834

Max Act: 0.9067. Min Act: -0.0000

Data Index: 1233021 (The Pile)

Max Activating Token Index: 862

Text #15

Max Range: 1.6834. Min Range: -1.6834

Max Act: 0.9006. Min Act: -0.0000

Data Index: 745712 (The Pile)

Max Activating Token Index: 371

Text #16

Max Range: 1.6834. Min Range: -1.6834

Max Act: 0.8945. Min Act: -0.0000

Data Index: 603765 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 1.6834. Min Range: -1.6834

Max Act: 0.8502. Min Act: -0.0000

Data Index: 495763 (The Pile)

Max Activating Token Index: 167

Text #18

Max Range: 1.6834. Min Range: -1.6834

Max Act: 0.8521. Min Act: -0.0000

Data Index: 1414936 (The Pile)

Max Activating Token Index: 359

Text #19

Max Range: 1.6834. Min Range: -1.6834

Max Act: 0.8119. Min Act: -0.0000

Data Index: 817530 (The Pile)

Max Activating Token Index: 779