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

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

Neuron 517 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.5739. Min Act: -0.0000

Data Index: 1293974 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.6361. Min Act: -0.0000

Data Index: 135791 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.4326. Min Act: -0.0000

Data Index: 1401389 (Python Code)

Max Activating Token Index: 210

Text #3

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.4179. Min Act: -0.0000

Data Index: 1475724 (Python Code)

Max Activating Token Index: 262

Text #4

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.3649. Min Act: -0.0000

Data Index: 898359 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.1604. Min Act: -0.0000

Data Index: 1160349 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.2867. Min Act: -0.0000

Data Index: 1606777 (Python Code)

Max Activating Token Index: 170

Text #7

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.2520. Min Act: -0.0000

Data Index: 1108664 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.2737. Min Act: -0.0000

Data Index: 817631 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.1779. Min Act: -0.0000

Data Index: 1365882 (Python Code)

Max Activating Token Index: 785

Text #10

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.3101. Min Act: -0.0000

Data Index: 866717 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.2171. Min Act: -0.0000

Data Index: 721709 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.2438. Min Act: -0.0000

Data Index: 262407 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.1535. Min Act: -0.0000

Data Index: 1032193 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.1837. Min Act: -0.0000

Data Index: 706725 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.1540. Min Act: -0.0000

Data Index: 33356 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.1387. Min Act: -0.0000

Data Index: 600373 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.0780. Min Act: -0.0000

Data Index: 731150 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.1590. Min Act: -0.0000

Data Index: 927933 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.0803. Min Act: 0.0000

Data Index: 1260294 (C4 (Web Text))

Max Activating Token Index: 963