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

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

Neuron 2652 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: 0.0921. Min Range: -0.0921

Max Act: 0.0921. Min Act: -0.0002

Data Index: 1648704 (Python Code)

Max Activating Token Index: 607

Text #1

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0744. Min Act: -0.0002

Data Index: 1443292 (Python Code)

Max Activating Token Index: 465

Text #2

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1393457 (Python Code)

Max Activating Token Index: 1003

Text #3

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1527875 (Python Code)

Max Activating Token Index: 906

Text #4

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0659. Min Act: -0.0002

Data Index: 907140 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1503039 (Python Code)

Max Activating Token Index: 944

Text #6

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0637. Min Act: -0.0002

Data Index: 1394636 (Python Code)

Max Activating Token Index: 178

Text #7

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1616667 (Python Code)

Max Activating Token Index: 687

Text #8

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1502605 (Python Code)

Max Activating Token Index: 207

Text #9

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1590461 (Python Code)

Max Activating Token Index: 961

Text #10

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1386508 (Python Code)

Max Activating Token Index: 779

Text #11

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1427970 (Python Code)

Max Activating Token Index: 776

Text #12

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1509123 (Python Code)

Max Activating Token Index: 397

Text #13

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1488850 (Python Code)

Max Activating Token Index: 132

Text #14

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1459524 (Python Code)

Max Activating Token Index: 457

Text #15

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1609501 (Python Code)

Max Activating Token Index: 536

Text #16

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1477852 (Python Code)

Max Activating Token Index: 853

Text #17

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1581092 (Python Code)

Max Activating Token Index: 1002

Text #18

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1526075 (Python Code)

Max Activating Token Index: 705

Text #19

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1523504 (Python Code)

Max Activating Token Index: 158