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

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

Neuron 5139 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: 0.0764. Min Range: -0.0764

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1493397 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0724. Min Act: -0.0002

Data Index: 1438292 (Python Code)

Max Activating Token Index: 808

Text #2

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1537703 (Python Code)

Max Activating Token Index: 829

Text #3

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1557940 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1639498 (Python Code)

Max Activating Token Index: 294

Text #5

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1589688 (Python Code)

Max Activating Token Index: 252

Text #6

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1656770 (Python Code)

Max Activating Token Index: 19

Text #7

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1583224 (Python Code)

Max Activating Token Index: 29

Text #8

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1399592 (Python Code)

Max Activating Token Index: 275

Text #9

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1462367 (Python Code)

Max Activating Token Index: 96

Text #10

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1431021 (Python Code)

Max Activating Token Index: 532

Text #11

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1428352 (Python Code)

Max Activating Token Index: 832

Text #12

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1477125 (Python Code)

Max Activating Token Index: 84

Text #13

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1438211 (Python Code)

Max Activating Token Index: 800

Text #14

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1655777 (Python Code)

Max Activating Token Index: 826

Text #15

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1655789 (Python Code)

Max Activating Token Index: 92

Text #16

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1607669 (Python Code)

Max Activating Token Index: 787

Text #17

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1415490 (Python Code)

Max Activating Token Index: 803

Text #18

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1428199 (Python Code)

Max Activating Token Index: 20

Text #19

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1608449 (Python Code)

Max Activating Token Index: 663