Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4895 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0720. Min Act: -0.0000

Data Index: 1299401 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0447. Min Act: -0.0000

Data Index: 1324194 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0597. Min Act: -0.0000

Data Index: 162192 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0565. Min Act: -0.0000

Data Index: 986620 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0561. Min Act: -0.0000

Data Index: 561635 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0585. Min Act: -0.0000

Data Index: 129928 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0524. Min Act: -0.0000

Data Index: 694656 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0544. Min Act: -0.0000

Data Index: 124869 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0550. Min Act: -0.0000

Data Index: 837067 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0566. Min Act: -0.0000

Data Index: 746505 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0486. Min Act: -0.0000

Data Index: 721039 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1456252 (Python Code)

Max Activating Token Index: 375

Text #12

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0499. Min Act: -0.0000

Data Index: 619758 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0510. Min Act: -0.0000

Data Index: 1419732 (Python Code)

Max Activating Token Index: 819

Text #14

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0497. Min Act: -0.0000

Data Index: 97121 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0456. Min Act: -0.0000

Data Index: 684911 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0489. Min Act: -0.0000

Data Index: 355254 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0519. Min Act: -0.0000

Data Index: 997838 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0437. Min Act: -0.0000

Data Index: 412075 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0473. Min Act: -0.0000

Data Index: 646971 (C4 (Web Text))

Max Activating Token Index: 751