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

Dataset: The Pile

Neuron 2203 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.5787. Min Act: -0.0000

Data Index: 160423 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.2649. Min Act: -0.0000

Data Index: 192556 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.2494. Min Act: -0.0000

Data Index: 845078 (The Pile)

Max Activating Token Index: 173

Text #3

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.3194. Min Act: -0.0000

Data Index: 1608942 (The Pile)

Max Activating Token Index: 123

Text #4

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.2868. Min Act: -0.0000

Data Index: 1486916 (The Pile)

Max Activating Token Index: 241

Text #5

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.4619. Min Act: -0.0000

Data Index: 1987675 (The Pile)

Max Activating Token Index: 190

Text #6

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.1801. Min Act: -0.0000

Data Index: 1045884 (The Pile)

Max Activating Token Index: 165

Text #7

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.2252. Min Act: -0.0000

Data Index: 866179 (The Pile)

Max Activating Token Index: 54

Text #8

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.1860. Min Act: -0.0000

Data Index: 830447 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.1657. Min Act: -0.0000

Data Index: 1767063 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.1396. Min Act: -0.0000

Data Index: 1095384 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.1929. Min Act: -0.0000

Data Index: 1002054 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.0645. Min Act: -0.0000

Data Index: 1819372 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 3.5787. Min Range: -3.5787

Max Act: 2.9182. Min Act: -0.0000

Data Index: 1341736 (The Pile)

Max Activating Token Index: 582

Text #14

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.0556. Min Act: -0.0000

Data Index: 1848810 (The Pile)

Max Activating Token Index: 6

Text #15

Max Range: 3.5787. Min Range: -3.5787

Max Act: 2.8993. Min Act: -0.0000

Data Index: 1501804 (The Pile)

Max Activating Token Index: 105

Text #16

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.0669. Min Act: -0.0000

Data Index: 452192 (The Pile)

Max Activating Token Index: 502

Text #17

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.0432. Min Act: -0.0000

Data Index: 1113745 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.0340. Min Act: -0.0000

Data Index: 613393 (The Pile)

Max Activating Token Index: 262

Text #19

Max Range: 3.5787. Min Range: -3.5787

Max Act: 2.9830. Min Act: -0.0000

Data Index: 50666 (The Pile)

Max Activating Token Index: 109