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

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

Neuron 538 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1451125 (Python Code)

Max Activating Token Index: 737

Text #1

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1421179 (Python Code)

Max Activating Token Index: 140

Text #2

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8994. Min Act: -0.0000

Data Index: 1531299 (Python Code)

Max Activating Token Index: 388

Text #3

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8620. Min Act: -0.0000

Data Index: 1648759 (Python Code)

Max Activating Token Index: 706

Text #4

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1561604 (Python Code)

Max Activating Token Index: 893

Text #5

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.7905. Min Act: -0.0000

Data Index: 1654985 (Python Code)

Max Activating Token Index: 360

Text #6

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.7810. Min Act: -0.0000

Data Index: 1574915 (Python Code)

Max Activating Token Index: 501

Text #7

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.8286. Min Act: -0.0000

Data Index: 1442741 (Python Code)

Max Activating Token Index: 476

Text #8

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6899. Min Act: -0.0000

Data Index: 1440028 (Python Code)

Max Activating Token Index: 355

Text #9

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.7693. Min Act: -0.0000

Data Index: 1515217 (Python Code)

Max Activating Token Index: 951

Text #10

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.7335. Min Act: -0.0000

Data Index: 1625594 (Python Code)

Max Activating Token Index: 551

Text #11

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.7554. Min Act: -0.0000

Data Index: 1446319 (Python Code)

Max Activating Token Index: 296

Text #12

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6505. Min Act: -0.0000

Data Index: 1496622 (Python Code)

Max Activating Token Index: 63

Text #13

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1423608 (Python Code)

Max Activating Token Index: 968

Text #14

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6369. Min Act: -0.0000

Data Index: 1616256 (Python Code)

Max Activating Token Index: 180

Text #15

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1434973 (Python Code)

Max Activating Token Index: 882

Text #16

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1386453 (Python Code)

Max Activating Token Index: 876

Text #17

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1506611 (Python Code)

Max Activating Token Index: 430

Text #18

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6567. Min Act: -0.0001

Data Index: 1366448 (Python Code)

Max Activating Token Index: 771

Text #19

Max Range: 0.8994. Min Range: -0.8994

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1495712 (Python Code)

Max Activating Token Index: 35