Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 468 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.7448. Min Act: -0.0000

Data Index: 1544762 (Python Code)

Max Activating Token Index: 600

Text #1

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1477890 (Python Code)

Max Activating Token Index: 914

Text #2

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1483148 (Python Code)

Max Activating Token Index: 586

Text #3

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.7342. Min Act: -0.0000

Data Index: 1508445 (Python Code)

Max Activating Token Index: 301

Text #4

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6949. Min Act: -0.0000

Data Index: 1452365 (Python Code)

Max Activating Token Index: 647

Text #5

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6743. Min Act: -0.0001

Data Index: 1562957 (Python Code)

Max Activating Token Index: 566

Text #6

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1601455 (Python Code)

Max Activating Token Index: 901

Text #7

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1505273 (Python Code)

Max Activating Token Index: 516

Text #8

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5815. Min Act: -0.0000

Data Index: 1626389 (Python Code)

Max Activating Token Index: 483

Text #9

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5291. Min Act: -0.0000

Data Index: 605982 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5051. Min Act: -0.0000

Data Index: 657439 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5302. Min Act: -0.0000

Data Index: 193551 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4897. Min Act: -0.0000

Data Index: 175473 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4551. Min Act: -0.0000

Data Index: 1174282 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4180. Min Act: -0.0000

Data Index: 984826 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4805. Min Act: -0.0000

Data Index: 110006 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4740. Min Act: -0.0000

Data Index: 68231 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4561. Min Act: -0.0000

Data Index: 489267 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4393. Min Act: -0.0000

Data Index: 104888 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4321. Min Act: -0.0000

Data Index: 827836 (C4 (Web Text))

Max Activating Token Index: 591