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

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

Neuron 3263 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1578080 (Python Code)

Max Activating Token Index: 734

Text #1

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1451791 (Python Code)

Max Activating Token Index: 1003

Text #2

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1444666 (Python Code)

Max Activating Token Index: 1000

Text #3

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1503124 (Python Code)

Max Activating Token Index: 711

Text #4

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1437081 (Python Code)

Max Activating Token Index: 341

Text #5

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1379756 (Python Code)

Max Activating Token Index: 733

Text #6

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1639234 (Python Code)

Max Activating Token Index: 791

Text #7

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1537926 (Python Code)

Max Activating Token Index: 965

Text #8

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1643552 (Python Code)

Max Activating Token Index: 967

Text #9

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1434057 (Python Code)

Max Activating Token Index: 162

Text #10

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1454884 (Python Code)

Max Activating Token Index: 355

Text #11

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1452172 (Python Code)

Max Activating Token Index: 597

Text #12

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1515717 (Python Code)

Max Activating Token Index: 376

Text #13

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1643891 (Python Code)

Max Activating Token Index: 295

Text #14

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6089. Min Act: -0.0000

Data Index: 1567529 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1605643 (Python Code)

Max Activating Token Index: 729

Text #16

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1575321 (Python Code)

Max Activating Token Index: 367

Text #17

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5535. Min Act: -0.0001

Data Index: 1579450 (Python Code)

Max Activating Token Index: 446

Text #18

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5876. Min Act: -0.0000

Data Index: 1438247 (Python Code)

Max Activating Token Index: 60

Text #19

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1504508 (Python Code)

Max Activating Token Index: 817