Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3546 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.4853. Min Act: -0.0001

Data Index: 864761 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.4853. Min Range: -1.4853

Max Act: 1.0145. Min Act: -0.0001

Data Index: 1590460 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.9016. Min Act: -0.0001

Data Index: 1615492 (Python Code)

Max Activating Token Index: 794

Text #3

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.8591. Min Act: -0.0001

Data Index: 1607493 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.7817. Min Act: -0.0001

Data Index: 1408337 (Python Code)

Max Activating Token Index: 133

Text #5

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.8670. Min Act: -0.0001

Data Index: 1598815 (Python Code)

Max Activating Token Index: 717

Text #6

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.8589. Min Act: -0.0001

Data Index: 1442139 (Python Code)

Max Activating Token Index: 941

Text #7

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.7407. Min Act: -0.0001

Data Index: 1556430 (Python Code)

Max Activating Token Index: 311

Text #8

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.8126. Min Act: -0.0001

Data Index: 1641208 (Python Code)

Max Activating Token Index: 941

Text #9

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.7791. Min Act: -0.0001

Data Index: 1555749 (Python Code)

Max Activating Token Index: 434

Text #10

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.7955. Min Act: -0.0001

Data Index: 1423850 (Python Code)

Max Activating Token Index: 912

Text #11

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.7949. Min Act: -0.0001

Data Index: 1612476 (Python Code)

Max Activating Token Index: 872

Text #12

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.7559. Min Act: -0.0001

Data Index: 1616032 (Python Code)

Max Activating Token Index: 956

Text #13

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.8225. Min Act: -0.0001

Data Index: 1492424 (Python Code)

Max Activating Token Index: 351

Text #14

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.7426. Min Act: -0.0001

Data Index: 1592400 (Python Code)

Max Activating Token Index: 76

Text #15

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.7622. Min Act: -0.0001

Data Index: 1368448 (Python Code)

Max Activating Token Index: 192

Text #16

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.7552. Min Act: -0.0001

Data Index: 1559652 (Python Code)

Max Activating Token Index: 488

Text #17

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.7166. Min Act: -0.0001

Data Index: 1440681 (Python Code)

Max Activating Token Index: 691

Text #18

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.7546. Min Act: -0.0001

Data Index: 1497696 (Python Code)

Max Activating Token Index: 194

Text #19

Max Range: 1.4853. Min Range: -1.4853

Max Act: 0.7307. Min Act: -0.0001

Data Index: 1476777 (Python Code)

Max Activating Token Index: 32