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

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

Neuron 5914 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0744. Min Range: -1.0744

Max Act: 1.0744. Min Act: -0.0000

Data Index: 1490454 (Python Code)

Max Activating Token Index: 137

Text #1

Max Range: 1.0744. Min Range: -1.0744

Max Act: 1.0481. Min Act: -0.0000

Data Index: 1208803 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.9954. Min Act: -0.0000

Data Index: 1632711 (Python Code)

Max Activating Token Index: 476

Text #3

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.9521. Min Act: -0.0000

Data Index: 1375161 (Python Code)

Max Activating Token Index: 640

Text #4

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.9270. Min Act: -0.0000

Data Index: 2182 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 1.0744. Min Range: -1.0744

Max Act: 1.0331. Min Act: -0.0000

Data Index: 1064953 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 1.0744. Min Range: -1.0744

Max Act: 1.0286. Min Act: -0.0000

Data Index: 1454283 (Python Code)

Max Activating Token Index: 884

Text #7

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.7972. Min Act: -0.0000

Data Index: 1367362 (Python Code)

Max Activating Token Index: 809

Text #8

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.8849. Min Act: -0.0000

Data Index: 822450 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 1.0744. Min Range: -1.0744

Max Act: 1.0376. Min Act: -0.0000

Data Index: 519795 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 1.0744. Min Range: -1.0744

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1424224 (Python Code)

Max Activating Token Index: 82

Text #11

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.9400. Min Act: -0.0000

Data Index: 53743 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.9100. Min Act: -0.0000

Data Index: 1552664 (Python Code)

Max Activating Token Index: 788

Text #13

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1070226 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.9554. Min Act: -0.0000

Data Index: 1442859 (Python Code)

Max Activating Token Index: 939

Text #15

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.9071. Min Act: -0.0000

Data Index: 1511363 (Python Code)

Max Activating Token Index: 682

Text #16

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.9609. Min Act: -0.0000

Data Index: 1373900 (Python Code)

Max Activating Token Index: 594

Text #17

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.9711. Min Act: -0.0000

Data Index: 886549 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.8260. Min Act: -0.0000

Data Index: 577359 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.9460. Min Act: -0.0000

Data Index: 464683 (C4 (Web Text))

Max Activating Token Index: 531