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

Dataset: The Pile

Neuron 328 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1506723 (The Pile)

Max Activating Token Index: 626

Text #1

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.1293. Min Act: -0.0000

Data Index: 623008 (The Pile)

Max Activating Token Index: 419

Text #2

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.0250. Min Act: -0.0000

Data Index: 1462362 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1968914 (The Pile)

Max Activating Token Index: 693

Text #4

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9008. Min Act: -0.0000

Data Index: 1517732 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.0259. Min Act: -0.0000

Data Index: 1839634 (The Pile)

Max Activating Token Index: 884

Text #6

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8151. Min Act: -0.0000

Data Index: 670456 (The Pile)

Max Activating Token Index: 618

Text #7

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9237. Min Act: -0.0000

Data Index: 616167 (The Pile)

Max Activating Token Index: 882

Text #8

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8547. Min Act: -0.0000

Data Index: 1057993 (The Pile)

Max Activating Token Index: 61

Text #9

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8969. Min Act: -0.0000

Data Index: 9005 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8484. Min Act: -0.0000

Data Index: 455934 (The Pile)

Max Activating Token Index: 33

Text #11

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1475396 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1357997 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8781. Min Act: -0.0000

Data Index: 1438720 (The Pile)

Max Activating Token Index: 163

Text #14

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.7956. Min Act: -0.0000

Data Index: 260478 (The Pile)

Max Activating Token Index: 151

Text #15

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1482679 (The Pile)

Max Activating Token Index: 695

Text #16

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8604. Min Act: -0.0000

Data Index: 970108 (The Pile)

Max Activating Token Index: 652

Text #17

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.7667. Min Act: -0.0000

Data Index: 1280430 (The Pile)

Max Activating Token Index: 735

Text #18

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.7421. Min Act: -0.0000

Data Index: 469262 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1670346 (The Pile)

Max Activating Token Index: 344