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

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

Neuron 1229 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: 1.4919. Min Range: -1.4919

Max Act: 1.4919. Min Act: -0.0000

Data Index: 1431334 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 1.4919. Min Range: -1.4919

Max Act: 1.3600. Min Act: -0.0000

Data Index: 1500223 (Python Code)

Max Activating Token Index: 302

Text #2

Max Range: 1.4919. Min Range: -1.4919

Max Act: 1.2334. Min Act: -0.0000

Data Index: 1646393 (Python Code)

Max Activating Token Index: 62

Text #3

Max Range: 1.4919. Min Range: -1.4919

Max Act: 1.0538. Min Act: -0.0000

Data Index: 1443867 (Python Code)

Max Activating Token Index: 957

Text #4

Max Range: 1.4919. Min Range: -1.4919

Max Act: 0.9181. Min Act: -0.0000

Data Index: 160451 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 1.4919. Min Range: -1.4919

Max Act: 0.9313. Min Act: -0.0000

Data Index: 173260 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 1.4919. Min Range: -1.4919

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1396056 (Python Code)

Max Activating Token Index: 721

Text #7

Max Range: 1.4919. Min Range: -1.4919

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1611788 (Python Code)

Max Activating Token Index: 847

Text #8

Max Range: 1.4919. Min Range: -1.4919

Max Act: 0.8502. Min Act: -0.0000

Data Index: 169961 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 1.4919. Min Range: -1.4919

Max Act: 0.8616. Min Act: -0.0000

Data Index: 871070 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 1.4919. Min Range: -1.4919

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1634359 (Python Code)

Max Activating Token Index: 718

Text #11

Max Range: 1.4919. Min Range: -1.4919

Max Act: 0.8415. Min Act: -0.0000

Data Index: 1510127 (Python Code)

Max Activating Token Index: 620

Text #12

Max Range: 1.4919. Min Range: -1.4919

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1017617 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 1.4919. Min Range: -1.4919

Max Act: 0.8435. Min Act: -0.0000

Data Index: 1442535 (Python Code)

Max Activating Token Index: 453

Text #14

Max Range: 1.4919. Min Range: -1.4919

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1525464 (Python Code)

Max Activating Token Index: 348

Text #15

Max Range: 1.4919. Min Range: -1.4919

Max Act: 0.8703. Min Act: -0.0000

Data Index: 1379431 (Python Code)

Max Activating Token Index: 780

Text #16

Max Range: 1.4919. Min Range: -1.4919

Max Act: 0.8099. Min Act: -0.0000

Data Index: 370310 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 1.4919. Min Range: -1.4919

Max Act: 0.8611. Min Act: -0.0000

Data Index: 1474638 (Python Code)

Max Activating Token Index: 393

Text #18

Max Range: 1.4919. Min Range: -1.4919

Max Act: 0.7976. Min Act: -0.0000

Data Index: 31873 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 1.4919. Min Range: -1.4919

Max Act: 0.7991. Min Act: -0.0000

Data Index: 25890 (C4 (Web Text))

Max Activating Token Index: 609