Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2702 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0051. Min Range: -2.0051

Max Act: 2.0051. Min Act: 0.0000

Data Index: 356101 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.7744. Min Act: -0.0000

Data Index: 630861 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.6597. Min Act: -0.0000

Data Index: 6390 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.7039. Min Act: 0.0000

Data Index: 216381 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.7997. Min Act: -0.0000

Data Index: 245059 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.6914. Min Act: -0.0000

Data Index: 1200743 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.5530. Min Act: -0.0000

Data Index: 1159698 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.4929. Min Act: -0.0000

Data Index: 1074550 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.5683. Min Act: 0.0000

Data Index: 590032 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.5503. Min Act: -0.0000

Data Index: 1114793 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.4827. Min Act: 0.0000

Data Index: 1129140 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.4658. Min Act: -0.0000

Data Index: 1086043 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.3707. Min Act: -0.0000

Data Index: 168911 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.4353. Min Act: -0.0000

Data Index: 141335 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.3551. Min Act: -0.0000

Data Index: 312528 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.4134. Min Act: 0.0001

Data Index: 195320 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.4179. Min Act: 0.0000

Data Index: 344492 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.3262. Min Act: -0.0000

Data Index: 1316531 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.3960. Min Act: -0.0000

Data Index: 999188 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 2.0051. Min Range: -2.0051

Max Act: 1.3021. Min Act: 0.0000

Data Index: 464169 (C4 (Web Text))

Max Activating Token Index: 735