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

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

Neuron 1633 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1439407 (Python Code)

Max Activating Token Index: 346

Text #1

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1479761 (Python Code)

Max Activating Token Index: 283

Text #2

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1472768 (Python Code)

Max Activating Token Index: 124

Text #3

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1391588 (Python Code)

Max Activating Token Index: 191

Text #4

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1570095 (Python Code)

Max Activating Token Index: 344

Text #5

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1514728 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1448702 (Python Code)

Max Activating Token Index: 796

Text #7

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1443673 (Python Code)

Max Activating Token Index: 171

Text #8

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3294. Min Act: -0.0000

Data Index: 1397045 (Python Code)

Max Activating Token Index: 33

Text #9

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1636836 (Python Code)

Max Activating Token Index: 32

Text #10

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1521887 (Python Code)

Max Activating Token Index: 151

Text #11

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1413598 (Python Code)

Max Activating Token Index: 70

Text #12

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1529375 (Python Code)

Max Activating Token Index: 941

Text #13

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3190. Min Act: -0.0000

Data Index: 1497602 (Python Code)

Max Activating Token Index: 331

Text #14

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.2824. Min Act: -0.0000

Data Index: 1403780 (Python Code)

Max Activating Token Index: 463

Text #15

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1425222 (Python Code)

Max Activating Token Index: 594

Text #16

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3147. Min Act: -0.0000

Data Index: 1438386 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1475124 (Python Code)

Max Activating Token Index: 888

Text #18

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1522968 (Python Code)

Max Activating Token Index: 602

Text #19

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1483176 (Python Code)

Max Activating Token Index: 532