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

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

Neuron 3355 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6655. Min Act: -0.0000

Data Index: 1213185 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1044614 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6269. Min Act: -0.0000

Data Index: 523096 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1115594 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5994. Min Act: -0.0000

Data Index: 929321 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5673. Min Act: -0.0000

Data Index: 89971 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5838. Min Act: -0.0000

Data Index: 981011 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5461. Min Act: -0.0000

Data Index: 834075 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1008834 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5227. Min Act: -0.0000

Data Index: 1066131 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5344. Min Act: -0.0000

Data Index: 480086 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5228. Min Act: -0.0000

Data Index: 789437 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5251. Min Act: -0.0000

Data Index: 945363 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5216. Min Act: 0.0000

Data Index: 963843 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5155. Min Act: -0.0000

Data Index: 285079 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4854. Min Act: -0.0000

Data Index: 168783 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5106. Min Act: -0.0000

Data Index: 920646 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4987. Min Act: -0.0000

Data Index: 1057827 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4812. Min Act: -0.0000

Data Index: 673298 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4845. Min Act: -0.0000

Data Index: 1076033 (C4 (Web Text))

Max Activating Token Index: 314