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

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

Neuron 491 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: 0.0793. Min Range: -0.0793

Max Act: 0.0762. Min Act: -0.0000

Data Index: 1500234 (Python Code)

Max Activating Token Index: 77

Text #1

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0793. Min Act: -0.0000

Data Index: 455581 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0608. Min Act: -0.0000

Data Index: 213165 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1587833 (Python Code)

Max Activating Token Index: 249

Text #4

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0620. Min Act: -0.0000

Data Index: 573575 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1645867 (Python Code)

Max Activating Token Index: 288

Text #6

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1441681 (Python Code)

Max Activating Token Index: 382

Text #7

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0577. Min Act: -0.0000

Data Index: 40664 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0532. Min Act: -0.0001

Data Index: 1455223 (Python Code)

Max Activating Token Index: 94

Text #9

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0573. Min Act: -0.0000

Data Index: 61891 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0558. Min Act: -0.0000

Data Index: 1106138 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0484. Min Act: -0.0000

Data Index: 406703 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1477105 (Python Code)

Max Activating Token Index: 99

Text #13

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0519. Min Act: -0.0000

Data Index: 261861 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0492. Min Act: -0.0000

Data Index: 713378 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1562333 (Python Code)

Max Activating Token Index: 94

Text #16

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1202239 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0523. Min Act: -0.0001

Data Index: 942741 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0543. Min Act: -0.0000

Data Index: 438005 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0485. Min Act: -0.0000

Data Index: 892841 (C4 (Web Text))

Max Activating Token Index: 398