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

Dataset: The Pile

Neuron 1335 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: 1.2391. Min Range: -1.2391

Max Act: 1.2391. Min Act: -0.0000

Data Index: 350723 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 1.2391. Min Range: -1.2391

Max Act: 1.0786. Min Act: -0.0000

Data Index: 1856 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 1.2391. Min Range: -1.2391

Max Act: 1.0313. Min Act: -0.0000

Data Index: 161568 (The Pile)

Max Activating Token Index: 11

Text #3

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8905. Min Act: -0.0000

Data Index: 716647 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 1.2391. Min Range: -1.2391

Max Act: 1.0078. Min Act: -0.0000

Data Index: 1754769 (The Pile)

Max Activating Token Index: 11

Text #5

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9260. Min Act: -0.0000

Data Index: 1256893 (The Pile)

Max Activating Token Index: 11

Text #6

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1153045 (The Pile)

Max Activating Token Index: 10

Text #7

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.9088. Min Act: -0.0000

Data Index: 728908 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8628. Min Act: -0.0000

Data Index: 1578116 (The Pile)

Max Activating Token Index: 21

Text #9

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8861. Min Act: -0.0000

Data Index: 355324 (The Pile)

Max Activating Token Index: 11

Text #10

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8643. Min Act: -0.0000

Data Index: 637039 (The Pile)

Max Activating Token Index: 27

Text #11

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1233701 (The Pile)

Max Activating Token Index: 17

Text #12

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1368552 (The Pile)

Max Activating Token Index: 11

Text #13

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1686585 (The Pile)

Max Activating Token Index: 14

Text #14

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.7653. Min Act: -0.0000

Data Index: 1368026 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1342252 (The Pile)

Max Activating Token Index: 17

Text #16

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1713157 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.6752. Min Act: -0.0000

Data Index: 40753 (The Pile)

Max Activating Token Index: 12

Text #18

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.7850. Min Act: -0.0000

Data Index: 1014701 (The Pile)

Max Activating Token Index: 25

Text #19

Max Range: 1.2391. Min Range: -1.2391

Max Act: 0.7776. Min Act: -0.0000

Data Index: 295724 (The Pile)

Max Activating Token Index: 11