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

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

Neuron 1135 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1602195 (Python Code)

Max Activating Token Index: 934

Text #1

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0757. Min Act: -0.0001

Data Index: 1610835 (Python Code)

Max Activating Token Index: 890

Text #2

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0739. Min Act: -0.0001

Data Index: 1644496 (Python Code)

Max Activating Token Index: 346

Text #3

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0703. Min Act: -0.0001

Data Index: 468583 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1481690 (Python Code)

Max Activating Token Index: 268

Text #5

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0717. Min Act: -0.0002

Data Index: 1076567 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1398807 (Python Code)

Max Activating Token Index: 885

Text #7

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0707. Min Act: -0.0001

Data Index: 498173 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0712. Min Act: -0.0002

Data Index: 719277 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1460479 (Python Code)

Max Activating Token Index: 314

Text #10

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0628. Min Act: -0.0001

Data Index: 517154 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0723. Min Act: -0.0002

Data Index: 927524 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0690. Min Act: -0.0001

Data Index: 853985 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1078464 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0680. Min Act: -0.0002

Data Index: 858113 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0697. Min Act: -0.0002

Data Index: 108385 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1653295 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0752. Min Act: -0.0001

Data Index: 1577803 (Python Code)

Max Activating Token Index: 240

Text #18

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0684. Min Act: -0.0001

Data Index: 733468 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0667. Min Act: -0.0001

Data Index: 313703 (C4 (Web Text))

Max Activating Token Index: 862