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

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

Neuron 4624 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1140. Min Act: -0.0000

Data Index: 5428 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1167. Min Act: -0.0000

Data Index: 457723 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1058. Min Act: -0.0000

Data Index: 221679 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0944. Min Act: -0.0000

Data Index: 191848 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1041784 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1094093 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0929. Min Act: -0.0000

Data Index: 1337356 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0947. Min Act: -0.0000

Data Index: 917761 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0913. Min Act: -0.0000

Data Index: 387079 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1348679 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0891. Min Act: -0.0000

Data Index: 603078 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0919. Min Act: -0.0000

Data Index: 839686 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0854. Min Act: -0.0000

Data Index: 79256 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0880. Min Act: -0.0000

Data Index: 200108 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0850. Min Act: -0.0000

Data Index: 404989 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1021302 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0877. Min Act: -0.0000

Data Index: 912362 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0841. Min Act: -0.0000

Data Index: 1014295 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0807. Min Act: 0.0000

Data Index: 460779 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0897. Min Act: 0.0000

Data Index: 37948 (C4 (Web Text))

Max Activating Token Index: 827