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

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

Neuron 1661 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: 0.9917. Min Range: -0.9917

Max Act: 0.9917. Min Act: -0.0001

Data Index: 739501 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.9240. Min Act: -0.0001

Data Index: 71803 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1277971 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8809. Min Act: -0.0000

Data Index: 596218 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8653. Min Act: -0.0001

Data Index: 1333417 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8992. Min Act: -0.0001

Data Index: 1187653 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7968. Min Act: -0.0001

Data Index: 64841 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8032. Min Act: -0.0001

Data Index: 796608 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8204. Min Act: -0.0001

Data Index: 854128 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7991. Min Act: -0.0001

Data Index: 664948 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7791. Min Act: -0.0001

Data Index: 999990 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7622. Min Act: -0.0001

Data Index: 514062 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7653. Min Act: -0.0001

Data Index: 482374 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7299. Min Act: -0.0001

Data Index: 144786 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7501. Min Act: -0.0001

Data Index: 1571287 (Python Code)

Max Activating Token Index: 542

Text #17

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7659. Min Act: -0.0001

Data Index: 37115 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7247. Min Act: -0.0000

Data Index: 651921 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.5493. Min Act: -0.0001

Data Index: 921193 (C4 (Web Text))

Max Activating Token Index: 915