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

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

Neuron 1230 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: 1.2376. Min Range: -1.2376

Max Act: 1.2376. Min Act: -0.0000

Data Index: 1542387 (Python Code)

Max Activating Token Index: 972

Text #1

Max Range: 1.2376. Min Range: -1.2376

Max Act: 1.1815. Min Act: -0.0000

Data Index: 674711 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 1.2376. Min Range: -1.2376

Max Act: 1.1751. Min Act: -0.0000

Data Index: 544476 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 1.2376. Min Range: -1.2376

Max Act: 1.1515. Min Act: -0.0000

Data Index: 1634554 (Python Code)

Max Activating Token Index: 588

Text #4

Max Range: 1.2376. Min Range: -1.2376

Max Act: 1.1712. Min Act: -0.0000

Data Index: 1600946 (Python Code)

Max Activating Token Index: 817

Text #5

Max Range: 1.2376. Min Range: -1.2376

Max Act: 1.0287. Min Act: -0.0000

Data Index: 75691 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 1.2376. Min Range: -1.2376

Max Act: 1.0868. Min Act: -0.0000

Data Index: 576413 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 1.2376. Min Range: -1.2376

Max Act: 1.0553. Min Act: -0.0000

Data Index: 969433 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.2376. Min Range: -1.2376

Max Act: 1.1915. Min Act: -0.0000

Data Index: 724485 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 1.2376. Min Range: -1.2376

Max Act: 1.0329. Min Act: -0.0000

Data Index: 169951 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1509424 (Python Code)

Max Activating Token Index: 527

Text #11

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.9935. Min Act: -0.0000

Data Index: 1560109 (Python Code)

Max Activating Token Index: 436

Text #12

Max Range: 1.2376. Min Range: -1.2376

Max Act: 1.0197. Min Act: -0.0000

Data Index: 425572 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.9996. Min Act: -0.0000

Data Index: 1124961 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 1.2376. Min Range: -1.2376

Max Act: 1.0620. Min Act: -0.0000

Data Index: 558201 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.9807. Min Act: -0.0000

Data Index: 636858 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.9874. Min Act: -0.0000

Data Index: 381240 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.9855. Min Act: -0.0000

Data Index: 1194215 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.9635. Min Act: -0.0000

Data Index: 1306918 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 1.2376. Min Range: -1.2376

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1085073 (C4 (Web Text))

Max Activating Token Index: 1021