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

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

Neuron 3714 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.6837. Min Act: -0.0001

Data Index: 553988 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1187186 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.5605. Min Act: -0.0000

Data Index: 32355 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.4846. Min Act: -0.0001

Data Index: 77338 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.4466. Min Act: -0.0000

Data Index: 244313 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1142681 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.4733. Min Act: -0.0000

Data Index: 486857 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.4211. Min Act: -0.0000

Data Index: 203764 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.4311. Min Act: -0.0000

Data Index: 850765 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.4483. Min Act: -0.0000

Data Index: 894613 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1321036 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.4083. Min Act: -0.0000

Data Index: 915114 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.4320. Min Act: -0.0000

Data Index: 180530 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.4144. Min Act: -0.0000

Data Index: 580523 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.3903. Min Act: -0.0000

Data Index: 743062 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.4045. Min Act: -0.0001

Data Index: 961035 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.4016. Min Act: -0.0001

Data Index: 249861 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.3957. Min Act: -0.0000

Data Index: 690755 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.3694. Min Act: -0.0001

Data Index: 553175 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.6837. Min Range: -0.6837

Max Act: 0.4090. Min Act: -0.0000

Data Index: 405886 (C4 (Web Text))

Max Activating Token Index: 573