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

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

Neuron 3539 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: 0.1170. Min Range: -0.1170

Max Act: 0.1170. Min Act: -0.0000

Data Index: 415662 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1534703 (Python Code)

Max Activating Token Index: 516

Text #2

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1517957 (Python Code)

Max Activating Token Index: 478

Text #3

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1528526 (Python Code)

Max Activating Token Index: 51

Text #4

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1430749 (Python Code)

Max Activating Token Index: 182

Text #5

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1430757 (Python Code)

Max Activating Token Index: 806

Text #6

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0882. Min Act: -0.0000

Data Index: 1555651 (Python Code)

Max Activating Token Index: 784

Text #7

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0944. Min Act: -0.0000

Data Index: 1505872 (Python Code)

Max Activating Token Index: 193

Text #8

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0904. Min Act: -0.0000

Data Index: 1347238 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1634726 (Python Code)

Max Activating Token Index: 914

Text #10

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0848. Min Act: -0.0000

Data Index: 706434 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1364528 (Python Code)

Max Activating Token Index: 335

Text #12

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1557620 (Python Code)

Max Activating Token Index: 580

Text #13

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0776. Min Act: -0.0000

Data Index: 1488268 (Python Code)

Max Activating Token Index: 337

Text #14

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0791. Min Act: -0.0000

Data Index: 1479758 (Python Code)

Max Activating Token Index: 282

Text #15

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0791. Min Act: -0.0000

Data Index: 1461387 (Python Code)

Max Activating Token Index: 568

Text #16

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1607951 (Python Code)

Max Activating Token Index: 241

Text #17

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1363032 (Python Code)

Max Activating Token Index: 425

Text #18

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1577375 (Python Code)

Max Activating Token Index: 311

Text #19

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0799. Min Act: -0.0000

Data Index: 1403387 (Python Code)

Max Activating Token Index: 446