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

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

Neuron 282 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: 0.6337. Min Range: -0.6337

Max Act: 0.5813. Min Act: -0.0000

Data Index: 361715 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5823. Min Act: -0.0000

Data Index: 5329 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5332. Min Act: -0.0000

Data Index: 962606 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.6337. Min Act: -0.0000

Data Index: 458933 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5430. Min Act: -0.0000

Data Index: 450036 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5504. Min Act: -0.0000

Data Index: 760255 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5536. Min Act: -0.0000

Data Index: 183786 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4654. Min Act: -0.0000

Data Index: 216426 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5625. Min Act: 0.0000

Data Index: 935936 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5075. Min Act: -0.0000

Data Index: 41508 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5047. Min Act: -0.0000

Data Index: 412362 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5343. Min Act: -0.0000

Data Index: 378983 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5233. Min Act: -0.0000

Data Index: 1251571 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5448. Min Act: -0.0000

Data Index: 20167 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5252. Min Act: -0.0000

Data Index: 1431231 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1102810 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4632. Min Act: -0.0000

Data Index: 307138 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4429. Min Act: -0.0000

Data Index: 427026 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1025050 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4604. Min Act: -0.0000

Data Index: 1169319 (C4 (Web Text))

Max Activating Token Index: 181