Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2274 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0830. Min Act: -0.0001

Data Index: 1488363 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0779. Min Act: -0.0001

Data Index: 1435332 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0726. Min Act: -0.0001

Data Index: 744542 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1505022 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1650115 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1645255 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0554. Min Act: -0.0001

Data Index: 873847 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1449676 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1389759 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1627798 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1389867 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0510. Min Act: -0.0001

Data Index: 1462812 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1491044 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1654409 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1599616 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0485. Min Act: -0.0001

Data Index: 1433510 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0485. Min Act: -0.0001

Data Index: 1507157 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0482. Min Act: -0.0001

Data Index: 1091310 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0470. Min Act: -0.0001

Data Index: 1425504 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0466. Min Act: -0.0001

Data Index: 1361259 (Python Code)

Max Activating Token Index: 1023