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

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

Neuron 1090 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: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0002

Data Index: 698413 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1376847 (Python Code)

Max Activating Token Index: 907

Text #2

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1635820 (Python Code)

Max Activating Token Index: 37

Text #3

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1446386 (Python Code)

Max Activating Token Index: 8

Text #4

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1410193 (Python Code)

Max Activating Token Index: 284

Text #5

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1484678 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1549161 (Python Code)

Max Activating Token Index: 151

Text #7

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1527950 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1573483 (Python Code)

Max Activating Token Index: 680

Text #9

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1370239 (Python Code)

Max Activating Token Index: 692

Text #10

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1627703 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1444878 (Python Code)

Max Activating Token Index: 747

Text #12

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1513197 (Python Code)

Max Activating Token Index: 641

Text #13

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0570. Min Act: -0.0002

Data Index: 54792 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1422790 (Python Code)

Max Activating Token Index: 681

Text #15

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1646092 (Python Code)

Max Activating Token Index: 500

Text #16

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1546082 (Python Code)

Max Activating Token Index: 737

Text #17

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0551. Min Act: -0.0002

Data Index: 315834 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1373530 (Python Code)

Max Activating Token Index: 920

Text #19

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1382031 (Python Code)

Max Activating Token Index: 28