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

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

Neuron 1850 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0835. Min Act: -0.0002

Data Index: 210954 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0608. Min Act: -0.0002

Data Index: 235992 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0573. Min Act: -0.0002

Data Index: 957459 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0501. Min Act: -0.0003

Data Index: 908203 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0510. Min Act: -0.0003

Data Index: 770417 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0491. Min Act: -0.0002

Data Index: 356422 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0469. Min Act: -0.0003

Data Index: 790930 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0465. Min Act: -0.0002

Data Index: 492263 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1255217 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0422. Min Act: -0.0002

Data Index: 664176 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0412. Min Act: -0.0003

Data Index: 960582 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0407. Min Act: -0.0002

Data Index: 445490 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0415. Min Act: -0.0003

Data Index: 202558 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0404. Min Act: -0.0002

Data Index: 513486 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0409. Min Act: -0.0002

Data Index: 488607 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0414. Min Act: -0.0002

Data Index: 175418 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0396. Min Act: -0.0002

Data Index: 973118 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0376. Min Act: -0.0002

Data Index: 210838 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0394. Min Act: -0.0003

Data Index: 243311 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0391. Min Act: -0.0003

Data Index: 476156 (C4 (Web Text))

Max Activating Token Index: 666