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

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

Neuron 4478 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: 0.4433. Min Range: -0.4433

Max Act: 0.4308. Min Act: -0.0000

Data Index: 546143 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.4433. Min Act: -0.0000

Data Index: 513271 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.4061. Min Act: -0.0000

Data Index: 934916 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3561. Min Act: -0.0000

Data Index: 90996 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3838. Min Act: -0.0000

Data Index: 119044 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1036617 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3684. Min Act: -0.0000

Data Index: 73140 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3438. Min Act: -0.0000

Data Index: 686353 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1265438 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1047857 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3346. Min Act: -0.0000

Data Index: 807711 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3348. Min Act: -0.0000

Data Index: 195208 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3121. Min Act: -0.0000

Data Index: 357401 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1049777 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3131. Min Act: -0.0000

Data Index: 642611 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.2922. Min Act: -0.0000

Data Index: 779499 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3312. Min Act: -0.0000

Data Index: 729972 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.3139. Min Act: -0.0000

Data Index: 219448 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1039694 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.4433. Min Range: -0.4433

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1322550 (C4 (Web Text))

Max Activating Token Index: 949