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

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

Neuron 627 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2184. Min Range: -5.2184

Max Act: 5.2184. Min Act: -0.0000

Data Index: 1631949 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.9272. Min Act: -0.0000

Data Index: 1432016 (Python Code)

Max Activating Token Index: 57

Text #2

Max Range: 5.2184. Min Range: -5.2184

Max Act: 5.1034. Min Act: -0.0000

Data Index: 1544640 (Python Code)

Max Activating Token Index: 91

Text #3

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.8742. Min Act: -0.0000

Data Index: 1442226 (Python Code)

Max Activating Token Index: 77

Text #4

Max Range: 5.2184. Min Range: -5.2184

Max Act: 5.0309. Min Act: -0.0000

Data Index: 1582251 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.6415. Min Act: -0.0000

Data Index: 1656620 (Python Code)

Max Activating Token Index: 790

Text #6

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.9339. Min Act: -0.0000

Data Index: 1403314 (Python Code)

Max Activating Token Index: 123

Text #7

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.5612. Min Act: -0.0000

Data Index: 1579002 (Python Code)

Max Activating Token Index: 481

Text #8

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.5290. Min Act: -0.0000

Data Index: 1597740 (Python Code)

Max Activating Token Index: 274

Text #9

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.5161. Min Act: -0.0000

Data Index: 1606601 (Python Code)

Max Activating Token Index: 168

Text #10

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.9795. Min Act: -0.0000

Data Index: 1645285 (Python Code)

Max Activating Token Index: 104

Text #11

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.6633. Min Act: -0.0000

Data Index: 1542095 (Python Code)

Max Activating Token Index: 887

Text #12

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.4332. Min Act: -0.0000

Data Index: 1564650 (Python Code)

Max Activating Token Index: 596

Text #13

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.7660. Min Act: -0.0000

Data Index: 1387599 (Python Code)

Max Activating Token Index: 588

Text #14

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.5840. Min Act: -0.0000

Data Index: 1572336 (Python Code)

Max Activating Token Index: 565

Text #15

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.4003. Min Act: -0.0000

Data Index: 1542828 (Python Code)

Max Activating Token Index: 758

Text #16

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.3594. Min Act: -0.0000

Data Index: 1571068 (Python Code)

Max Activating Token Index: 26

Text #17

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.5377. Min Act: -0.0000

Data Index: 1636360 (Python Code)

Max Activating Token Index: 386

Text #18

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.6996. Min Act: -0.0000

Data Index: 1387593 (Python Code)

Max Activating Token Index: 149

Text #19

Max Range: 5.2184. Min Range: -5.2184

Max Act: 4.4393. Min Act: -0.0000

Data Index: 1603026 (Python Code)

Max Activating Token Index: 527