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

Dataset: The Pile

Neuron 3658 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: 1.2832. Min Range: -1.2832

Max Act: 1.2537. Min Act: -0.0000

Data Index: 1440534 (The Pile)

Max Activating Token Index: 116

Text #1

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.2832. Min Act: -0.0000

Data Index: 32291 (The Pile)

Max Activating Token Index: 696

Text #2

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.2726. Min Act: -0.0000

Data Index: 211605 (The Pile)

Max Activating Token Index: 964

Text #3

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.1383. Min Act: -0.0000

Data Index: 1889153 (The Pile)

Max Activating Token Index: 408

Text #4

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1279949 (The Pile)

Max Activating Token Index: 985

Text #5

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.1146. Min Act: -0.0000

Data Index: 547836 (The Pile)

Max Activating Token Index: 119

Text #6

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.1003. Min Act: -0.0000

Data Index: 774531 (The Pile)

Max Activating Token Index: 68

Text #7

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1787281 (The Pile)

Max Activating Token Index: 822

Text #8

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.0402. Min Act: -0.0000

Data Index: 759743 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.1346. Min Act: -0.0000

Data Index: 1488677 (The Pile)

Max Activating Token Index: 340

Text #10

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.0052. Min Act: -0.0000

Data Index: 1013448 (The Pile)

Max Activating Token Index: 202

Text #11

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1629123 (The Pile)

Max Activating Token Index: 105

Text #12

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.0247. Min Act: -0.0000

Data Index: 704250 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.0140. Min Act: -0.0000

Data Index: 833040 (The Pile)

Max Activating Token Index: 72

Text #14

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.0729. Min Act: -0.0000

Data Index: 861469 (The Pile)

Max Activating Token Index: 413

Text #15

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.9691. Min Act: -0.0000

Data Index: 590798 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.0193. Min Act: -0.0000

Data Index: 561082 (The Pile)

Max Activating Token Index: 985

Text #17

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.0271. Min Act: -0.0000

Data Index: 1370279 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.1077. Min Act: -0.0000

Data Index: 68878 (The Pile)

Max Activating Token Index: 194

Text #19

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1663066 (The Pile)

Max Activating Token Index: 979