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

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

Neuron 5831 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: 0.8981. Min Range: -0.8981

Max Act: 0.8981. Min Act: -0.0000

Data Index: 21221 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7429. Min Act: -0.0000

Data Index: 235106 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7646. Min Act: -0.0000

Data Index: 556476 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1129319 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7026. Min Act: -0.0000

Data Index: 389435 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7275. Min Act: -0.0000

Data Index: 718991 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6979. Min Act: -0.0000

Data Index: 522068 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7119. Min Act: -0.0000

Data Index: 235348 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6993. Min Act: -0.0000

Data Index: 9329 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7708. Min Act: -0.0000

Data Index: 336047 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7129. Min Act: -0.0000

Data Index: 881610 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6629. Min Act: -0.0000

Data Index: 918920 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.7308. Min Act: -0.0000

Data Index: 371525 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1291780 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6603. Min Act: -0.0000

Data Index: 231133 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6186. Min Act: -0.0000

Data Index: 549584 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1087071 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6156. Min Act: -0.0000

Data Index: 405587 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6038. Min Act: -0.0000

Data Index: 806721 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.6190. Min Act: -0.0000

Data Index: 914724 (C4 (Web Text))

Max Activating Token Index: 527