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

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

Neuron 518 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3555. Min Range: -1.3555

Max Act: 1.3555. Min Act: -0.0000

Data Index: 1575289 (Python Code)

Max Activating Token Index: 321

Text #1

Max Range: 1.3555. Min Range: -1.3555

Max Act: 1.0771. Min Act: -0.0000

Data Index: 1117742 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 1.3555. Min Range: -1.3555

Max Act: 1.0024. Min Act: -0.0000

Data Index: 1589014 (Python Code)

Max Activating Token Index: 518

Text #3

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1602531 (Python Code)

Max Activating Token Index: 169

Text #4

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1580834 (Python Code)

Max Activating Token Index: 943

Text #5

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1570861 (Python Code)

Max Activating Token Index: 675

Text #6

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7661. Min Act: -0.0000

Data Index: 1515455 (Python Code)

Max Activating Token Index: 873

Text #7

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7640. Min Act: -0.0000

Data Index: 1654645 (Python Code)

Max Activating Token Index: 804

Text #8

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1578369 (Python Code)

Max Activating Token Index: 902

Text #9

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7464. Min Act: -0.0000

Data Index: 205706 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.8048. Min Act: -0.0000

Data Index: 1632666 (Python Code)

Max Activating Token Index: 451

Text #11

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7442. Min Act: -0.0000

Data Index: 1224915 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1621584 (Python Code)

Max Activating Token Index: 195

Text #13

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1602255 (Python Code)

Max Activating Token Index: 129

Text #14

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1591200 (Python Code)

Max Activating Token Index: 494

Text #15

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7522. Min Act: -0.0000

Data Index: 63611 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7480. Min Act: -0.0000

Data Index: 374634 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7310. Min Act: -0.0000

Data Index: 831086 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1385485 (Python Code)

Max Activating Token Index: 85

Text #19

Max Range: 1.3555. Min Range: -1.3555

Max Act: 0.7523. Min Act: -0.0000

Data Index: 1537570 (Python Code)

Max Activating Token Index: 931