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

Dataset: The Pile

Neuron 2378 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: 0.9471. Min Range: -0.9471

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1849298 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.9125. Min Act: -0.0000

Data Index: 1257031 (The Pile)

Max Activating Token Index: 574

Text #2

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.8775. Min Act: -0.0000

Data Index: 612314 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.8291. Min Act: -0.0000

Data Index: 728009 (The Pile)

Max Activating Token Index: 36

Text #4

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1219211 (The Pile)

Max Activating Token Index: 525

Text #5

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.8497. Min Act: -0.0000

Data Index: 733090 (The Pile)

Max Activating Token Index: 59

Text #6

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.8192. Min Act: -0.0000

Data Index: 1632728 (The Pile)

Max Activating Token Index: 1006

Text #7

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1521516 (The Pile)

Max Activating Token Index: 399

Text #8

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.8093. Min Act: -0.0000

Data Index: 1025661 (The Pile)

Max Activating Token Index: 815

Text #9

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.8021. Min Act: -0.0000

Data Index: 1458770 (The Pile)

Max Activating Token Index: 31

Text #10

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.8297. Min Act: -0.0000

Data Index: 564452 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.8173. Min Act: -0.0000

Data Index: 859348 (The Pile)

Max Activating Token Index: 62

Text #12

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.7853. Min Act: -0.0000

Data Index: 921847 (The Pile)

Max Activating Token Index: 866

Text #13

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1564798 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.8324. Min Act: -0.0000

Data Index: 1079353 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.7711. Min Act: -0.0000

Data Index: 693175 (The Pile)

Max Activating Token Index: 972

Text #16

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.7956. Min Act: -0.0000

Data Index: 814422 (The Pile)

Max Activating Token Index: 985

Text #17

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.7950. Min Act: -0.0000

Data Index: 36358 (The Pile)

Max Activating Token Index: 350

Text #18

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.8423. Min Act: -0.0000

Data Index: 232065 (The Pile)

Max Activating Token Index: 995

Text #19

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.7666. Min Act: -0.0000

Data Index: 1277574 (The Pile)

Max Activating Token Index: 255