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

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

Neuron 3253 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: 1.8519. Min Range: -1.8519

Max Act: 1.8470. Min Act: -0.0000

Data Index: 1615987 (Python Code)

Max Activating Token Index: 68

Text #1

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.7960. Min Act: -0.0000

Data Index: 1620853 (Python Code)

Max Activating Token Index: 415

Text #2

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.8519. Min Act: -0.0000

Data Index: 1415442 (Python Code)

Max Activating Token Index: 912

Text #3

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.6369. Min Act: -0.0000

Data Index: 1399602 (Python Code)

Max Activating Token Index: 309

Text #4

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.5370. Min Act: -0.0000

Data Index: 1586385 (Python Code)

Max Activating Token Index: 657

Text #5

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.5683. Min Act: -0.0000

Data Index: 1157022 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.4103. Min Act: -0.0000

Data Index: 1450322 (Python Code)

Max Activating Token Index: 327

Text #7

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.5636. Min Act: -0.0000

Data Index: 1432992 (Python Code)

Max Activating Token Index: 784

Text #8

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.4419. Min Act: -0.0000

Data Index: 1512415 (Python Code)

Max Activating Token Index: 821

Text #9

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.3503. Min Act: -0.0000

Data Index: 1480648 (Python Code)

Max Activating Token Index: 283

Text #10

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.4019. Min Act: -0.0000

Data Index: 1557967 (Python Code)

Max Activating Token Index: 822

Text #11

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.3820. Min Act: -0.0000

Data Index: 1060203 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.4086. Min Act: -0.0000

Data Index: 1483199 (Python Code)

Max Activating Token Index: 582

Text #13

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.3986. Min Act: -0.0000

Data Index: 1652817 (Python Code)

Max Activating Token Index: 528

Text #14

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.3984. Min Act: -0.0000

Data Index: 1461106 (Python Code)

Max Activating Token Index: 584

Text #15

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.4025. Min Act: -0.0000

Data Index: 1381037 (Python Code)

Max Activating Token Index: 818

Text #16

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.3357. Min Act: -0.0000

Data Index: 1559807 (Python Code)

Max Activating Token Index: 866

Text #17

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.2720. Min Act: -0.0000

Data Index: 1430893 (Python Code)

Max Activating Token Index: 414

Text #18

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.4156. Min Act: -0.0000

Data Index: 1604376 (Python Code)

Max Activating Token Index: 33

Text #19

Max Range: 1.8519. Min Range: -1.8519

Max Act: 1.3359. Min Act: -0.0000

Data Index: 1566076 (Python Code)

Max Activating Token Index: 467