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

Dataset: The Pile

Neuron 3112 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0031. Min Range: -3.0031

Max Act: 3.0031. Min Act: -0.0000

Data Index: 434276 (The Pile)

Max Activating Token Index: 18

Text #1

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.4509. Min Act: -0.0000

Data Index: 1163585 (The Pile)

Max Activating Token Index: 726

Text #2

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.4051. Min Act: -0.0000

Data Index: 36531 (The Pile)

Max Activating Token Index: 18

Text #3

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.2290. Min Act: -0.0000

Data Index: 1034457 (The Pile)

Max Activating Token Index: 531

Text #4

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.0779. Min Act: -0.0000

Data Index: 1456909 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 3.0031. Min Range: -3.0031

Max Act: 1.9837. Min Act: -0.0000

Data Index: 540891 (The Pile)

Max Activating Token Index: 205

Text #6

Max Range: 3.0031. Min Range: -3.0031

Max Act: 1.8890. Min Act: -0.0000

Data Index: 760464 (The Pile)

Max Activating Token Index: 909

Text #7

Max Range: 3.0031. Min Range: -3.0031

Max Act: 1.8580. Min Act: -0.0000

Data Index: 1666203 (The Pile)

Max Activating Token Index: 638

Text #8

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.1463. Min Act: -0.0000

Data Index: 1954121 (The Pile)

Max Activating Token Index: 238

Text #9

Max Range: 3.0031. Min Range: -3.0031

Max Act: 1.8948. Min Act: -0.0000

Data Index: 614772 (The Pile)

Max Activating Token Index: 424

Text #10

Max Range: 3.0031. Min Range: -3.0031

Max Act: 1.9678. Min Act: -0.0000

Data Index: 1342009 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 3.0031. Min Range: -3.0031

Max Act: 1.8753. Min Act: -0.0000

Data Index: 1616386 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 3.0031. Min Range: -3.0031

Max Act: 1.7712. Min Act: -0.0000

Data Index: 632376 (The Pile)

Max Activating Token Index: 157

Text #13

Max Range: 3.0031. Min Range: -3.0031

Max Act: 1.7651. Min Act: -0.0000

Data Index: 1609158 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 3.0031. Min Range: -3.0031

Max Act: 1.8535. Min Act: -0.0000

Data Index: 687283 (The Pile)

Max Activating Token Index: 960

Text #15

Max Range: 3.0031. Min Range: -3.0031

Max Act: 1.6500. Min Act: -0.0000

Data Index: 721875 (The Pile)

Max Activating Token Index: 759

Text #16

Max Range: 3.0031. Min Range: -3.0031

Max Act: 1.8484. Min Act: -0.0000

Data Index: 1478757 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 3.0031. Min Range: -3.0031

Max Act: 1.7175. Min Act: -0.0000

Data Index: 1528529 (The Pile)

Max Activating Token Index: 986

Text #18

Max Range: 3.0031. Min Range: -3.0031

Max Act: 1.8370. Min Act: -0.0000

Data Index: 1821377 (The Pile)

Max Activating Token Index: 773

Text #19

Max Range: 3.0031. Min Range: -3.0031

Max Act: 1.7924. Min Act: -0.0000

Data Index: 459513 (The Pile)

Max Activating Token Index: 312