Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2707 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0670. Min Act: -0.0001

Data Index: 810679 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0636. Min Act: -0.0001

Data Index: 96228 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0583. Min Act: -0.0000

Data Index: 146579 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0575. Min Act: -0.0001

Data Index: 958217 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0558. Min Act: -0.0001

Data Index: 877045 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0565. Min Act: -0.0001

Data Index: 666288 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0519. Min Act: -0.0001

Data Index: 964566 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1168559 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1086754 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0505. Min Act: -0.0000

Data Index: 1244291 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0506. Min Act: -0.0001

Data Index: 1551710 (Python Code)

Max Activating Token Index: 517

Text #11

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1173539 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0504. Min Act: -0.0000

Data Index: 514122 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0496. Min Act: -0.0001

Data Index: 148795 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0501. Min Act: -0.0001

Data Index: 163276 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0493. Min Act: -0.0001

Data Index: 650360 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0476. Min Act: -0.0000

Data Index: 227526 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0473. Min Act: -0.0000

Data Index: 270865 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0504. Min Act: -0.0001

Data Index: 363915 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0465. Min Act: -0.0001

Data Index: 520738 (C4 (Web Text))

Max Activating Token Index: 760