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

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

Neuron 3290 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0984. Min Act: -0.0001

Data Index: 637833 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1557873 (Python Code)

Max Activating Token Index: 886

Text #2

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1438602 (Python Code)

Max Activating Token Index: 540

Text #3

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1390199 (Python Code)

Max Activating Token Index: 493

Text #4

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1578595 (Python Code)

Max Activating Token Index: 329

Text #5

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1617567 (Python Code)

Max Activating Token Index: 57

Text #6

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1391893 (Python Code)

Max Activating Token Index: 900

Text #7

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0538. Min Act: -0.0001

Data Index: 212568 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0494. Min Act: -0.0001

Data Index: 215034 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0414. Min Act: -0.0001

Data Index: 1484190 (Python Code)

Max Activating Token Index: 328

Text #10

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1389169 (Python Code)

Max Activating Token Index: 269

Text #11

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1388952 (Python Code)

Max Activating Token Index: 694

Text #12

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1377834 (Python Code)

Max Activating Token Index: 41

Text #13

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1488974 (Python Code)

Max Activating Token Index: 920

Text #14

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1648366 (Python Code)

Max Activating Token Index: 907

Text #15

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0414. Min Act: -0.0001

Data Index: 1437430 (Python Code)

Max Activating Token Index: 600

Text #16

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1613836 (Python Code)

Max Activating Token Index: 670

Text #17

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0399. Min Act: -0.0001

Data Index: 1437626 (Python Code)

Max Activating Token Index: 793

Text #18

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0374. Min Act: -0.0001

Data Index: 110327 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0382. Min Act: -0.0001

Data Index: 1552854 (Python Code)

Max Activating Token Index: 231