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

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

Neuron 1657 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1549487 (Python Code)

Max Activating Token Index: 1014

Text #1

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8493. Min Act: -0.0000

Data Index: 1456797 (Python Code)

Max Activating Token Index: 930

Text #2

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1562548 (Python Code)

Max Activating Token Index: 940

Text #3

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1653350 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.7862. Min Act: 0.0000

Data Index: 1620902 (Python Code)

Max Activating Token Index: 1011

Text #5

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.7692. Min Act: -0.0000

Data Index: 61340 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.7352. Min Act: 0.0000

Data Index: 1629507 (Python Code)

Max Activating Token Index: 238

Text #7

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8120. Min Act: -0.0000

Data Index: 1379661 (Python Code)

Max Activating Token Index: 914

Text #8

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.7003. Min Act: -0.0000

Data Index: 929094 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1470394 (Python Code)

Max Activating Token Index: 488

Text #10

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1461309 (Python Code)

Max Activating Token Index: 360

Text #11

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.7360. Min Act: 0.0000

Data Index: 1410581 (Python Code)

Max Activating Token Index: 390

Text #12

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1413472 (Python Code)

Max Activating Token Index: 434

Text #13

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1372693 (Python Code)

Max Activating Token Index: 704

Text #14

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6010. Min Act: 0.0000

Data Index: 1447605 (Python Code)

Max Activating Token Index: 571

Text #15

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1652652 (Python Code)

Max Activating Token Index: 394

Text #16

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6544. Min Act: -0.0000

Data Index: 218466 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1353888 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.5699. Min Act: 0.0000

Data Index: 1379876 (Python Code)

Max Activating Token Index: 922

Text #19

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6040. Min Act: -0.0000

Data Index: 442844 (C4 (Web Text))

Max Activating Token Index: 112