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

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

Neuron 3326 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: 0.2988. Min Range: -0.2988

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1362649 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1629264 (Python Code)

Max Activating Token Index: 805

Text #2

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1383261 (Python Code)

Max Activating Token Index: 237

Text #3

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1443401 (Python Code)

Max Activating Token Index: 665

Text #4

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1565272 (Python Code)

Max Activating Token Index: 86

Text #5

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1465071 (Python Code)

Max Activating Token Index: 979

Text #6

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1488069 (Python Code)

Max Activating Token Index: 86

Text #7

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1425605 (Python Code)

Max Activating Token Index: 357

Text #8

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1396947 (Python Code)

Max Activating Token Index: 522

Text #9

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1624386 (Python Code)

Max Activating Token Index: 365

Text #10

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2080. Min Act: -0.0000

Data Index: 1647504 (Python Code)

Max Activating Token Index: 377

Text #11

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1946. Min Act: -0.0000

Data Index: 735556 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1441806 (Python Code)

Max Activating Token Index: 355

Text #13

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1841. Min Act: -0.0000

Data Index: 233518 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1841. Min Act: -0.0000

Data Index: 320658 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1500437 (Python Code)

Max Activating Token Index: 525

Text #16

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1889. Min Act: -0.0000

Data Index: 764901 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1085662 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1574406 (Python Code)

Max Activating Token Index: 630

Text #19

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1397202 (Python Code)

Max Activating Token Index: 933