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

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

Neuron 5037 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.7711. Min Act: 0.0000

Data Index: 1654162 (Python Code)

Max Activating Token Index: 550

Text #1

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1632251 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1517847 (Python Code)

Max Activating Token Index: 939

Text #3

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1451528 (Python Code)

Max Activating Token Index: 282

Text #4

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6813. Min Act: 0.0000

Data Index: 1615038 (Python Code)

Max Activating Token Index: 577

Text #5

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6773. Min Act: 0.0000

Data Index: 1626964 (Python Code)

Max Activating Token Index: 585

Text #6

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1465084 (Python Code)

Max Activating Token Index: 98

Text #7

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6526. Min Act: 0.0000

Data Index: 1568075 (Python Code)

Max Activating Token Index: 301

Text #8

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6369. Min Act: -0.0000

Data Index: 1620189 (Python Code)

Max Activating Token Index: 290

Text #9

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1369357 (Python Code)

Max Activating Token Index: 930

Text #10

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1424405 (Python Code)

Max Activating Token Index: 769

Text #11

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1439630 (Python Code)

Max Activating Token Index: 753

Text #12

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6176. Min Act: 0.0000

Data Index: 1583797 (Python Code)

Max Activating Token Index: 544

Text #13

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6292. Min Act: 0.0000

Data Index: 1612371 (Python Code)

Max Activating Token Index: 42

Text #14

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1443572 (Python Code)

Max Activating Token Index: 667

Text #15

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6025. Min Act: 0.0000

Data Index: 1450816 (Python Code)

Max Activating Token Index: 263

Text #16

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6139. Min Act: -0.0000

Data Index: 1465268 (Python Code)

Max Activating Token Index: 764

Text #17

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1611590 (Python Code)

Max Activating Token Index: 288

Text #18

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1516790 (Python Code)

Max Activating Token Index: 915

Text #19

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1542983 (Python Code)

Max Activating Token Index: 844