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

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

Neuron 1915 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.0853. Min Act: -0.0000

Data Index: 711463 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.1222. Min Act: -0.0000

Data Index: 631275 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.1372. Min Act: -0.0000

Data Index: 1250015 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.1088. Min Act: -0.0000

Data Index: 382000 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 1.1372. Min Range: -1.1372

Max Act: 1.1302. Min Act: -0.0000

Data Index: 1533009 (Python Code)

Max Activating Token Index: 585

Text #5

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9812. Min Act: -0.0000

Data Index: 989925 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9578. Min Act: -0.0000

Data Index: 552213 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1277787 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1200732 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9850. Min Act: -0.0000

Data Index: 54137 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9453. Min Act: -0.0000

Data Index: 345314 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1045508 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9046. Min Act: -0.0000

Data Index: 326824 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9315. Min Act: -0.0000

Data Index: 185187 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9060. Min Act: -0.0000

Data Index: 1043349 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8476. Min Act: -0.0000

Data Index: 693042 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8382. Min Act: -0.0000

Data Index: 885652 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.9158. Min Act: -0.0000

Data Index: 81131 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8884. Min Act: -0.0000

Data Index: 422495 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 1.1372. Min Range: -1.1372

Max Act: 0.8518. Min Act: -0.0000

Data Index: 33740 (C4 (Web Text))

Max Activating Token Index: 62