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

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

Neuron 5698 in Layer 0

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: 0.0562. Min Range: -0.0562

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1600832 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1526723 (Python Code)

Max Activating Token Index: 928

Text #2

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1593481 (Python Code)

Max Activating Token Index: 1008

Text #3

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0518. Min Act: -0.0001

Data Index: 1543521 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1440616 (Python Code)

Max Activating Token Index: 43

Text #5

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0502. Min Act: -0.0001

Data Index: 1516698 (Python Code)

Max Activating Token Index: 1007

Text #6

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1402199 (Python Code)

Max Activating Token Index: 161

Text #7

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1559236 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0501. Min Act: -0.0001

Data Index: 1436942 (Python Code)

Max Activating Token Index: 983

Text #9

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1646556 (Python Code)

Max Activating Token Index: 957

Text #10

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0506. Min Act: -0.0001

Data Index: 1454301 (Python Code)

Max Activating Token Index: 911

Text #11

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1509695 (Python Code)

Max Activating Token Index: 87

Text #12

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0501. Min Act: -0.0001

Data Index: 1431265 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0495. Min Act: -0.0001

Data Index: 1477735 (Python Code)

Max Activating Token Index: 369

Text #14

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0488. Min Act: -0.0001

Data Index: 1552753 (Python Code)

Max Activating Token Index: 56

Text #15

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1554962 (Python Code)

Max Activating Token Index: 123

Text #16

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1398891 (Python Code)

Max Activating Token Index: 234

Text #17

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0485. Min Act: -0.0001

Data Index: 1582952 (Python Code)

Max Activating Token Index: 128

Text #18

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0484. Min Act: -0.0001

Data Index: 1489173 (Python Code)

Max Activating Token Index: 67

Text #19

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1646992 (Python Code)

Max Activating Token Index: 212