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

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

Neuron 3867 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0634. Min Act: -0.0002

Data Index: 198840 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0637. Min Act: -0.0002

Data Index: 205640 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1347526 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1005881 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0580. Min Act: -0.0002

Data Index: 360263 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0551. Min Act: -0.0002

Data Index: 606527 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1196046 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0553. Min Act: -0.0002

Data Index: 881064 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0512. Min Act: -0.0002

Data Index: 187932 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0495. Min Act: -0.0002

Data Index: 253620 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0490. Min Act: -0.0002

Data Index: 685383 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0479. Min Act: -0.0002

Data Index: 691209 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0469. Min Act: -0.0002

Data Index: 629086 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0467. Min Act: -0.0002

Data Index: 656534 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0432. Min Act: -0.0002

Data Index: 764418 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0461. Min Act: -0.0002

Data Index: 207302 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0476. Min Act: -0.0002

Data Index: 669335 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0461. Min Act: -0.0002

Data Index: 266025 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0482. Min Act: -0.0002

Data Index: 730350 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1078803 (C4 (Web Text))

Max Activating Token Index: 370