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

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

Neuron 1739 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5872. Min Range: -2.5872

Max Act: 2.5872. Min Act: -0.0000

Data Index: 1388392 (Python Code)

Max Activating Token Index: 133

Text #1

Max Range: 2.5872. Min Range: -2.5872

Max Act: 2.4965. Min Act: -0.0000

Data Index: 1422966 (Python Code)

Max Activating Token Index: 382

Text #2

Max Range: 2.5872. Min Range: -2.5872

Max Act: 2.1785. Min Act: -0.0001

Data Index: 1632838 (Python Code)

Max Activating Token Index: 109

Text #3

Max Range: 2.5872. Min Range: -2.5872

Max Act: 2.1101. Min Act: -0.0000

Data Index: 1420750 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 2.5872. Min Range: -2.5872

Max Act: 2.1002. Min Act: -0.0001

Data Index: 1515012 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 2.5872. Min Range: -2.5872

Max Act: 2.0382. Min Act: -0.0000

Data Index: 1515535 (Python Code)

Max Activating Token Index: 540

Text #6

Max Range: 2.5872. Min Range: -2.5872

Max Act: 1.8794. Min Act: -0.0001

Data Index: 1439310 (Python Code)

Max Activating Token Index: 501

Text #7

Max Range: 2.5872. Min Range: -2.5872

Max Act: 1.9665. Min Act: -0.0000

Data Index: 1374936 (Python Code)

Max Activating Token Index: 574

Text #8

Max Range: 2.5872. Min Range: -2.5872

Max Act: 1.8596. Min Act: -0.0001

Data Index: 1593747 (Python Code)

Max Activating Token Index: 929

Text #9

Max Range: 2.5872. Min Range: -2.5872

Max Act: 1.7871. Min Act: -0.0000

Data Index: 1378120 (Python Code)

Max Activating Token Index: 75

Text #10

Max Range: 2.5872. Min Range: -2.5872

Max Act: 1.9376. Min Act: -0.0000

Data Index: 1392143 (Python Code)

Max Activating Token Index: 783

Text #11

Max Range: 2.5872. Min Range: -2.5872

Max Act: 1.6786. Min Act: -0.0000

Data Index: 1464742 (Python Code)

Max Activating Token Index: 220

Text #12

Max Range: 2.5872. Min Range: -2.5872

Max Act: 1.6511. Min Act: -0.0000

Data Index: 1381159 (Python Code)

Max Activating Token Index: 771

Text #13

Max Range: 2.5872. Min Range: -2.5872

Max Act: 1.6263. Min Act: -0.0000

Data Index: 1441639 (Python Code)

Max Activating Token Index: 910

Text #14

Max Range: 2.5872. Min Range: -2.5872

Max Act: 1.6248. Min Act: -0.0000

Data Index: 1427174 (Python Code)

Max Activating Token Index: 562

Text #15

Max Range: 2.5872. Min Range: -2.5872

Max Act: 1.5834. Min Act: -0.0001

Data Index: 1478715 (Python Code)

Max Activating Token Index: 414

Text #16

Max Range: 2.5872. Min Range: -2.5872

Max Act: 1.6543. Min Act: -0.0000

Data Index: 1356709 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 2.5872. Min Range: -2.5872

Max Act: 1.5559. Min Act: -0.0001

Data Index: 1469464 (Python Code)

Max Activating Token Index: 92

Text #18

Max Range: 2.5872. Min Range: -2.5872

Max Act: 1.6170. Min Act: -0.0000

Data Index: 1563469 (Python Code)

Max Activating Token Index: 298

Text #19

Max Range: 2.5872. Min Range: -2.5872

Max Act: 1.5721. Min Act: -0.0000

Data Index: 1623863 (Python Code)

Max Activating Token Index: 192