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

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

Neuron 5490 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1155711 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5474. Min Act: -0.0000

Data Index: 135912 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5127. Min Act: -0.0000

Data Index: 488604 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5060. Min Act: -0.0000

Data Index: 447382 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4887. Min Act: -0.0000

Data Index: 33870 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4819. Min Act: -0.0000

Data Index: 640124 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4928. Min Act: -0.0000

Data Index: 415468 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5255. Min Act: -0.0000

Data Index: 313488 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1508932 (Python Code)

Max Activating Token Index: 327

Text #9

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4771. Min Act: -0.0000

Data Index: 431918 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4731. Min Act: -0.0000

Data Index: 290282 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4792. Min Act: -0.0000

Data Index: 184365 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4577. Min Act: -0.0000

Data Index: 221001 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1199397 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1486172 (Python Code)

Max Activating Token Index: 388

Text #15

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4700. Min Act: -0.0000

Data Index: 539340 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4615. Min Act: -0.0000

Data Index: 825228 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1246331 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4514. Min Act: -0.0000

Data Index: 309692 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4969. Min Act: -0.0000

Data Index: 581766 (C4 (Web Text))

Max Activating Token Index: 239