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

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

Neuron 3993 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.8577. Min Act: -0.0000

Data Index: 739105 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.7177. Min Act: -0.0000

Data Index: 799644 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.6504. Min Act: -0.0000

Data Index: 761229 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.6202. Min Act: -0.0000

Data Index: 1404024 (Python Code)

Max Activating Token Index: 269

Text #4

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.5298. Min Act: -0.0000

Data Index: 422460 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.6315. Min Act: -0.0000

Data Index: 423414 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.6845. Min Act: -0.0000

Data Index: 1178663 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.5335. Min Act: -0.0000

Data Index: 206895 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.5274. Min Act: -0.0000

Data Index: 1224024 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.4506. Min Act: -0.0000

Data Index: 691740 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.4551. Min Act: -0.0000

Data Index: 534407 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.3203. Min Act: -0.0000

Data Index: 1405063 (Python Code)

Max Activating Token Index: 862

Text #12

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.4515. Min Act: -0.0000

Data Index: 787601 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.4299. Min Act: -0.0000

Data Index: 1625535 (Python Code)

Max Activating Token Index: 38

Text #14

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.3438. Min Act: -0.0000

Data Index: 1002376 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.4095. Min Act: -0.0000

Data Index: 1391002 (Python Code)

Max Activating Token Index: 448

Text #16

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.3958. Min Act: -0.0000

Data Index: 437893 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.3813. Min Act: -0.0000

Data Index: 630883 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.2922. Min Act: -0.0000

Data Index: 1446591 (Python Code)

Max Activating Token Index: 941

Text #19

Max Range: 1.8577. Min Range: -1.8577

Max Act: 1.2631. Min Act: -0.0000

Data Index: 1152657 (C4 (Web Text))

Max Activating Token Index: 618