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

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

Neuron 4013 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.9415. Min Act: -0.0000

Data Index: 753962 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.9161. Min Act: 0.0000

Data Index: 796274 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.8604. Min Act: -0.0000

Data Index: 137565 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1080444 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6346. Min Act: -0.0000

Data Index: 421320 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6141. Min Act: 0.0000

Data Index: 347573 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6365. Min Act: -0.0000

Data Index: 518343 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5597. Min Act: -0.0000

Data Index: 529209 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5751. Min Act: -0.0000

Data Index: 478551 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1619032 (Python Code)

Max Activating Token Index: 476

Text #10

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5537. Min Act: -0.0000

Data Index: 1296049 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1034375 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5464. Min Act: -0.0000

Data Index: 552744 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1077136 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1642919 (Python Code)

Max Activating Token Index: 253

Text #15

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5011. Min Act: 0.0000

Data Index: 497052 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5733. Min Act: -0.0000

Data Index: 658221 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1399368 (Python Code)

Max Activating Token Index: 281

Text #18

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5146. Min Act: -0.0000

Data Index: 292933 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1433101 (Python Code)

Max Activating Token Index: 638