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

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

Neuron 1614 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8981. Min Range: -7.8981

Max Act: 7.8981. Min Act: -0.0000

Data Index: 1394016 (Python Code)

Max Activating Token Index: 460

Text #1

Max Range: 7.8981. Min Range: -7.8981

Max Act: 7.6608. Min Act: -0.0000

Data Index: 1435966 (Python Code)

Max Activating Token Index: 444

Text #2

Max Range: 7.8981. Min Range: -7.8981

Max Act: 7.5597. Min Act: -0.0000

Data Index: 1482437 (Python Code)

Max Activating Token Index: 580

Text #3

Max Range: 7.8981. Min Range: -7.8981

Max Act: 7.5341. Min Act: -0.0000

Data Index: 1555678 (Python Code)

Max Activating Token Index: 411

Text #4

Max Range: 7.8981. Min Range: -7.8981

Max Act: 7.4282. Min Act: -0.0000

Data Index: 1407507 (Python Code)

Max Activating Token Index: 486

Text #5

Max Range: 7.8981. Min Range: -7.8981

Max Act: 7.5628. Min Act: -0.0000

Data Index: 1483073 (Python Code)

Max Activating Token Index: 503

Text #6

Max Range: 7.8981. Min Range: -7.8981

Max Act: 7.2501. Min Act: -0.0000

Data Index: 1366365 (Python Code)

Max Activating Token Index: 933

Text #7

Max Range: 7.8981. Min Range: -7.8981

Max Act: 7.3896. Min Act: -0.0000

Data Index: 1467997 (Python Code)

Max Activating Token Index: 328

Text #8

Max Range: 7.8981. Min Range: -7.8981

Max Act: 7.1710. Min Act: -0.0000

Data Index: 1461774 (Python Code)

Max Activating Token Index: 477

Text #9

Max Range: 7.8981. Min Range: -7.8981

Max Act: 6.8591. Min Act: -0.0000

Data Index: 1433342 (Python Code)

Max Activating Token Index: 349

Text #10

Max Range: 7.8981. Min Range: -7.8981

Max Act: 7.0653. Min Act: -0.0000

Data Index: 1484646 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 7.8981. Min Range: -7.8981

Max Act: 6.8608. Min Act: -0.0000

Data Index: 1520266 (Python Code)

Max Activating Token Index: 496

Text #12

Max Range: 7.8981. Min Range: -7.8981

Max Act: 6.6287. Min Act: -0.0000

Data Index: 1523179 (Python Code)

Max Activating Token Index: 706

Text #13

Max Range: 7.8981. Min Range: -7.8981

Max Act: 6.5831. Min Act: -0.0000

Data Index: 1550747 (Python Code)

Max Activating Token Index: 954

Text #14

Max Range: 7.8981. Min Range: -7.8981

Max Act: 6.5653. Min Act: -0.0000

Data Index: 1611996 (Python Code)

Max Activating Token Index: 92

Text #15

Max Range: 7.8981. Min Range: -7.8981

Max Act: 6.3871. Min Act: -0.0000

Data Index: 1482342 (Python Code)

Max Activating Token Index: 897

Text #16

Max Range: 7.8981. Min Range: -7.8981

Max Act: 6.1579. Min Act: -0.0000

Data Index: 1641171 (Python Code)

Max Activating Token Index: 366

Text #17

Max Range: 7.8981. Min Range: -7.8981

Max Act: 6.3775. Min Act: -0.0000

Data Index: 1362146 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 7.8981. Min Range: -7.8981

Max Act: 6.1152. Min Act: -0.0000

Data Index: 1536484 (Python Code)

Max Activating Token Index: 526

Text #19

Max Range: 7.8981. Min Range: -7.8981

Max Act: 5.9051. Min Act: -0.0000

Data Index: 1563085 (Python Code)

Max Activating Token Index: 891