Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1846 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1628353 (Python Code)

Max Activating Token Index: 881

Text #1

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0618. Min Act: -0.0003

Data Index: 794907 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0582. Min Act: -0.0003

Data Index: 1636136 (Python Code)

Max Activating Token Index: 797

Text #3

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0627. Min Act: -0.0003

Data Index: 1473752 (Python Code)

Max Activating Token Index: 428

Text #4

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0574. Min Act: -0.0003

Data Index: 339485 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0597. Min Act: -0.0003

Data Index: 1414531 (Python Code)

Max Activating Token Index: 936

Text #6

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0589. Min Act: -0.0003

Data Index: 1418756 (Python Code)

Max Activating Token Index: 267

Text #7

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0573. Min Act: -0.0003

Data Index: 1614694 (Python Code)

Max Activating Token Index: 912

Text #8

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0560. Min Act: -0.0003

Data Index: 1599990 (Python Code)

Max Activating Token Index: 115

Text #9

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1445847 (Python Code)

Max Activating Token Index: 154

Text #10

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0567. Min Act: -0.0003

Data Index: 1111095 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1036836 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1489159 (Python Code)

Max Activating Token Index: 119

Text #13

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1529253 (Python Code)

Max Activating Token Index: 718

Text #14

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1563561 (Python Code)

Max Activating Token Index: 229

Text #15

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1589985 (Python Code)

Max Activating Token Index: 387

Text #16

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1523359 (Python Code)

Max Activating Token Index: 987

Text #17

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0522. Min Act: -0.0003

Data Index: 862026 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0521. Min Act: -0.0003

Data Index: 1307234 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0530. Min Act: -0.0003

Data Index: 594505 (C4 (Web Text))

Max Activating Token Index: 281