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

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

Neuron 679 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.6019. Min Act: -0.0000

Data Index: 191020 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.6413. Min Act: -0.0000

Data Index: 39929 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.5584. Min Act: -0.0000

Data Index: 18256 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.5531. Min Act: -0.0000

Data Index: 1323509 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.4392. Min Act: -0.0000

Data Index: 476761 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.4237. Min Act: -0.0000

Data Index: 61331 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.3727. Min Act: -0.0000

Data Index: 1231668 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.3716. Min Act: -0.0000

Data Index: 1197895 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.1816. Min Act: -0.0000

Data Index: 18792 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.2660. Min Act: -0.0000

Data Index: 355275 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.1568. Min Act: -0.0000

Data Index: 65805 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.0718. Min Act: 0.0000

Data Index: 211690 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.0676. Min Act: -0.0000

Data Index: 314496 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.1053. Min Act: -0.0000

Data Index: 979070 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.1778. Min Act: -0.0000

Data Index: 356636 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.1037. Min Act: -0.0000

Data Index: 1308083 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.0944. Min Act: -0.0000

Data Index: 1140509 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.1278. Min Act: -0.0000

Data Index: 404834 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.0682. Min Act: -0.0000

Data Index: 1158734 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 1.6413. Min Range: -1.6413

Max Act: 1.1335. Min Act: -0.0000

Data Index: 775598 (C4 (Web Text))

Max Activating Token Index: 544