Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2725 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0730. Min Range: -1.0730

Max Act: 1.0706. Min Act: -0.0002

Data Index: 1466578 (Python Code)

Max Activating Token Index: 119

Text #1

Max Range: 1.0730. Min Range: -1.0730

Max Act: 1.0730. Min Act: -0.0002

Data Index: 1503691 (Python Code)

Max Activating Token Index: 136

Text #2

Max Range: 1.0730. Min Range: -1.0730

Max Act: 1.0170. Min Act: -0.0002

Data Index: 1430517 (Python Code)

Max Activating Token Index: 832

Text #3

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.8901. Min Act: -0.0002

Data Index: 1500242 (Python Code)

Max Activating Token Index: 735

Text #4

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.9110. Min Act: -0.0002

Data Index: 1592557 (Python Code)

Max Activating Token Index: 406

Text #5

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.8792. Min Act: -0.0002

Data Index: 1479480 (Python Code)

Max Activating Token Index: 71

Text #6

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.8842. Min Act: -0.0002

Data Index: 1439257 (Python Code)

Max Activating Token Index: 190

Text #7

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.8615. Min Act: -0.0002

Data Index: 1611757 (Python Code)

Max Activating Token Index: 969

Text #8

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.8695. Min Act: -0.0002

Data Index: 1393223 (Python Code)

Max Activating Token Index: 356

Text #9

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.8298. Min Act: -0.0002

Data Index: 1642943 (Python Code)

Max Activating Token Index: 604

Text #10

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.8041. Min Act: -0.0002

Data Index: 1541890 (Python Code)

Max Activating Token Index: 834

Text #11

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.7707. Min Act: -0.0002

Data Index: 1586956 (Python Code)

Max Activating Token Index: 793

Text #12

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.7589. Min Act: -0.0002

Data Index: 1518595 (Python Code)

Max Activating Token Index: 303

Text #13

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.7088. Min Act: -0.0002

Data Index: 1587633 (Python Code)

Max Activating Token Index: 590

Text #14

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.7077. Min Act: -0.0002

Data Index: 1540692 (Python Code)

Max Activating Token Index: 735

Text #15

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.7509. Min Act: -0.0002

Data Index: 1404502 (Python Code)

Max Activating Token Index: 323

Text #16

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.7190. Min Act: -0.0002

Data Index: 1582280 (Python Code)

Max Activating Token Index: 864

Text #17

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.7286. Min Act: -0.0002

Data Index: 1652721 (Python Code)

Max Activating Token Index: 538

Text #18

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.7860. Min Act: -0.0002

Data Index: 1631781 (Python Code)

Max Activating Token Index: 896

Text #19

Max Range: 1.0730. Min Range: -1.0730

Max Act: 0.7210. Min Act: -0.0002

Data Index: 1498939 (Python Code)

Max Activating Token Index: 714