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

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

Neuron 4636 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1023237 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5328. Min Act: -0.0000

Data Index: 68172 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5632. Min Act: -0.0000

Data Index: 980050 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5003. Min Act: -0.0000

Data Index: 1138851 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5141. Min Act: -0.0000

Data Index: 256968 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5259. Min Act: -0.0000

Data Index: 660670 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4723. Min Act: -0.0000

Data Index: 69214 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4999. Min Act: -0.0000

Data Index: 748495 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4249. Min Act: -0.0000

Data Index: 479655 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1205722 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1142404 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4512. Min Act: -0.0000

Data Index: 412790 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1086721 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.3732. Min Act: -0.0000

Data Index: 215400 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4452. Min Act: -0.0000

Data Index: 352385 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4407. Min Act: -0.0000

Data Index: 512389 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4230. Min Act: -0.0000

Data Index: 473082 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4483. Min Act: -0.0000

Data Index: 199158 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4124. Min Act: -0.0000

Data Index: 365023 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.3875. Min Act: -0.0000

Data Index: 649689 (C4 (Web Text))

Max Activating Token Index: 114