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

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

Neuron 275 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.4806. Min Act: -0.0000

Data Index: 1360504 (Python Code)

Max Activating Token Index: 622

Text #1

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.3439. Min Act: -0.0000

Data Index: 1596192 (Python Code)

Max Activating Token Index: 478

Text #2

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.1989. Min Act: -0.0000

Data Index: 1419101 (Python Code)

Max Activating Token Index: 286

Text #3

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.1856. Min Act: -0.0000

Data Index: 1617052 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.1704. Min Act: -0.0000

Data Index: 1617005 (Python Code)

Max Activating Token Index: 244

Text #5

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.2759. Min Act: -0.0000

Data Index: 1628076 (Python Code)

Max Activating Token Index: 764

Text #6

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.1620. Min Act: -0.0000

Data Index: 1593817 (Python Code)

Max Activating Token Index: 367

Text #7

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.2769. Min Act: -0.0000

Data Index: 1633049 (Python Code)

Max Activating Token Index: 113

Text #8

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.2594. Min Act: -0.0000

Data Index: 1626272 (Python Code)

Max Activating Token Index: 600

Text #9

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.2491. Min Act: -0.0000

Data Index: 1382410 (Python Code)

Max Activating Token Index: 83

Text #10

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.2392. Min Act: -0.0000

Data Index: 1430826 (Python Code)

Max Activating Token Index: 645

Text #11

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.2334. Min Act: -0.0000

Data Index: 1461860 (Python Code)

Max Activating Token Index: 414

Text #12

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.2217. Min Act: -0.0000

Data Index: 1492376 (Python Code)

Max Activating Token Index: 28

Text #13

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.3248. Min Act: -0.0000

Data Index: 1459255 (Python Code)

Max Activating Token Index: 440

Text #14

Max Range: 2.4806. Min Range: -2.4806

Max Act: 1.9559. Min Act: -0.0000

Data Index: 1457104 (Python Code)

Max Activating Token Index: 768

Text #15

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.0772. Min Act: -0.0000

Data Index: 1445439 (Python Code)

Max Activating Token Index: 167

Text #16

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.1690. Min Act: -0.0000

Data Index: 1582426 (Python Code)

Max Activating Token Index: 46

Text #17

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.0528. Min Act: -0.0000

Data Index: 1496791 (Python Code)

Max Activating Token Index: 106

Text #18

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.1736. Min Act: -0.0000

Data Index: 1599589 (Python Code)

Max Activating Token Index: 121

Text #19

Max Range: 2.4806. Min Range: -2.4806

Max Act: 2.1449. Min Act: -0.0000

Data Index: 1382851 (Python Code)

Max Activating Token Index: 155