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

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

Neuron 3051 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.7881. Min Act: -0.0000

Data Index: 1417313 (Python Code)

Max Activating Token Index: 225

Text #1

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5224. Min Act: -0.0000

Data Index: 1523595 (Python Code)

Max Activating Token Index: 587

Text #2

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5365. Min Act: -0.0000

Data Index: 1371049 (Python Code)

Max Activating Token Index: 554

Text #3

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.4339. Min Act: -0.0000

Data Index: 1385454 (Python Code)

Max Activating Token Index: 125

Text #4

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5121. Min Act: -0.0000

Data Index: 1513585 (Python Code)

Max Activating Token Index: 799

Text #5

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.4548. Min Act: -0.0000

Data Index: 1617772 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.3711. Min Act: -0.0000

Data Index: 1618517 (Python Code)

Max Activating Token Index: 241

Text #7

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.3458. Min Act: -0.0000

Data Index: 1104227 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.2798. Min Act: -0.0000

Data Index: 1367350 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.2614. Min Act: -0.0000

Data Index: 1393182 (Python Code)

Max Activating Token Index: 304

Text #10

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.2537. Min Act: -0.0000

Data Index: 1624717 (Python Code)

Max Activating Token Index: 890

Text #11

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.1799. Min Act: -0.0000

Data Index: 1430594 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.3270. Min Act: -0.0000

Data Index: 1454350 (Python Code)

Max Activating Token Index: 546

Text #13

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.2323. Min Act: 0.0000

Data Index: 1491180 (Python Code)

Max Activating Token Index: 719

Text #14

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.1632. Min Act: -0.0000

Data Index: 1363372 (Python Code)

Max Activating Token Index: 883

Text #15

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.2164. Min Act: -0.0000

Data Index: 1370244 (Python Code)

Max Activating Token Index: 490

Text #16

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.2113. Min Act: -0.0000

Data Index: 1366638 (Python Code)

Max Activating Token Index: 780

Text #17

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.2886. Min Act: -0.0000

Data Index: 1555608 (Python Code)

Max Activating Token Index: 526

Text #18

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.1387. Min Act: -0.0000

Data Index: 1633365 (Python Code)

Max Activating Token Index: 994

Text #19

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.0391. Min Act: -0.0000

Data Index: 371365 (C4 (Web Text))

Max Activating Token Index: 709