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

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

Neuron 3996 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.9603. Min Act: -0.0000

Data Index: 219422 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1434669 (Python Code)

Max Activating Token Index: 49

Text #2

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.9122. Min Act: -0.0000

Data Index: 1293426 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8392. Min Act: -0.0000

Data Index: 322214 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1617231 (Python Code)

Max Activating Token Index: 785

Text #5

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8643. Min Act: -0.0000

Data Index: 103409 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8440. Min Act: -0.0000

Data Index: 1231209 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8878. Min Act: -0.0000

Data Index: 358598 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1254878 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8525. Min Act: -0.0000

Data Index: 397442 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8662. Min Act: -0.0000

Data Index: 1121415 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8697. Min Act: -0.0000

Data Index: 800269 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8121. Min Act: -0.0000

Data Index: 736281 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8367. Min Act: -0.0000

Data Index: 242151 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8375. Min Act: -0.0000

Data Index: 284419 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8445. Min Act: -0.0000

Data Index: 672530 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1471778 (Python Code)

Max Activating Token Index: 386

Text #17

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1565406 (Python Code)

Max Activating Token Index: 181

Text #18

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1338498 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.7823. Min Act: -0.0000

Data Index: 320885 (C4 (Web Text))

Max Activating Token Index: 508