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

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

Neuron 4442 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0870. Min Range: -1.0870

Max Act: 1.0870. Min Act: -0.0000

Data Index: 628960 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 1.0870. Min Range: -1.0870

Max Act: 1.0365. Min Act: -0.0000

Data Index: 760281 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.9214. Min Act: -0.0000

Data Index: 654620 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.8102. Min Act: -0.0000

Data Index: 607382 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.9282. Min Act: -0.0000

Data Index: 252687 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.8665. Min Act: -0.0000

Data Index: 735024 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.8678. Min Act: -0.0000

Data Index: 82850 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.8640. Min Act: 0.0000

Data Index: 828452 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1288600 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.8454. Min Act: -0.0000

Data Index: 256676 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.7996. Min Act: -0.0000

Data Index: 464382 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.7762. Min Act: 0.0000

Data Index: 504904 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.7935. Min Act: -0.0000

Data Index: 933088 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.8010. Min Act: -0.0000

Data Index: 537463 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.7400. Min Act: -0.0000

Data Index: 921110 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1304288 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.7173. Min Act: -0.0000

Data Index: 909335 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.7132. Min Act: 0.0000

Data Index: 640807 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.6629. Min Act: -0.0000

Data Index: 807909 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 1.0870. Min Range: -1.0870

Max Act: 0.6614. Min Act: -0.0000

Data Index: 979849 (C4 (Web Text))

Max Activating Token Index: 874