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

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

Neuron 594 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3659. Min Range: -1.3659

Max Act: 1.3659. Min Act: -0.0001

Data Index: 1460049 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 1.3659. Min Range: -1.3659

Max Act: 1.2472. Min Act: -0.0000

Data Index: 39287 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 1.3659. Min Range: -1.3659

Max Act: 1.2685. Min Act: -0.0000

Data Index: 1390774 (Python Code)

Max Activating Token Index: 26

Text #3

Max Range: 1.3659. Min Range: -1.3659

Max Act: 1.1819. Min Act: -0.0000

Data Index: 1561234 (Python Code)

Max Activating Token Index: 127

Text #4

Max Range: 1.3659. Min Range: -1.3659

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1538457 (Python Code)

Max Activating Token Index: 928

Text #5

Max Range: 1.3659. Min Range: -1.3659

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1562593 (Python Code)

Max Activating Token Index: 114

Text #6

Max Range: 1.3659. Min Range: -1.3659

Max Act: 1.0996. Min Act: -0.0000

Data Index: 1448079 (Python Code)

Max Activating Token Index: 145

Text #7

Max Range: 1.3659. Min Range: -1.3659

Max Act: 1.0765. Min Act: -0.0000

Data Index: 1643260 (Python Code)

Max Activating Token Index: 783

Text #8

Max Range: 1.3659. Min Range: -1.3659

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1523871 (Python Code)

Max Activating Token Index: 337

Text #9

Max Range: 1.3659. Min Range: -1.3659

Max Act: 1.1065. Min Act: -0.0000

Data Index: 1499722 (Python Code)

Max Activating Token Index: 565

Text #10

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.9745. Min Act: -0.0000

Data Index: 443566 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1576110 (Python Code)

Max Activating Token Index: 319

Text #12

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.9883. Min Act: -0.0000

Data Index: 1420885 (Python Code)

Max Activating Token Index: 56

Text #13

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1609998 (Python Code)

Max Activating Token Index: 894

Text #14

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1446342 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.9878. Min Act: -0.0001

Data Index: 1069524 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1442290 (Python Code)

Max Activating Token Index: 870

Text #17

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1585622 (Python Code)

Max Activating Token Index: 512

Text #18

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1507708 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.9689. Min Act: -0.0000

Data Index: 1498274 (Python Code)

Max Activating Token Index: 553