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

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

Neuron 6025 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1630354 (Python Code)

Max Activating Token Index: 722

Text #1

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0669. Min Act: -0.0002

Data Index: 1560586 (Python Code)

Max Activating Token Index: 239

Text #2

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1421287 (Python Code)

Max Activating Token Index: 688

Text #3

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1615771 (Python Code)

Max Activating Token Index: 177

Text #4

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1427780 (Python Code)

Max Activating Token Index: 367

Text #5

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1547909 (Python Code)

Max Activating Token Index: 310

Text #6

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1396789 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1629722 (Python Code)

Max Activating Token Index: 971

Text #8

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1502294 (Python Code)

Max Activating Token Index: 57

Text #9

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1483251 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1485635 (Python Code)

Max Activating Token Index: 686

Text #11

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1487364 (Python Code)

Max Activating Token Index: 312

Text #12

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1483880 (Python Code)

Max Activating Token Index: 947

Text #13

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1619444 (Python Code)

Max Activating Token Index: 271

Text #14

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1446536 (Python Code)

Max Activating Token Index: 73

Text #15

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1656338 (Python Code)

Max Activating Token Index: 822

Text #16

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1597156 (Python Code)

Max Activating Token Index: 416

Text #17

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1423643 (Python Code)

Max Activating Token Index: 25

Text #18

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1553666 (Python Code)

Max Activating Token Index: 645

Text #19

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1485232 (Python Code)

Max Activating Token Index: 1008