Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 170 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.9382. Min Act: -0.0001

Data Index: 508476 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1174293 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.8452. Min Act: -0.0001

Data Index: 702144 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7446. Min Act: -0.0001

Data Index: 814179 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7423. Min Act: -0.0001

Data Index: 1220419 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6917. Min Act: -0.0000

Data Index: 709823 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7286. Min Act: -0.0001

Data Index: 688785 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7125. Min Act: -0.0001

Data Index: 960795 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6923. Min Act: -0.0000

Data Index: 1354884 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6906. Min Act: -0.0000

Data Index: 705956 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6895. Min Act: -0.0001

Data Index: 1159023 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6853. Min Act: -0.0000

Data Index: 514899 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6966. Min Act: -0.0001

Data Index: 1108546 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6536. Min Act: -0.0001

Data Index: 616208 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6698. Min Act: -0.0001

Data Index: 218970 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6855. Min Act: -0.0001

Data Index: 1079844 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6824. Min Act: -0.0000

Data Index: 901378 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6275. Min Act: -0.0000

Data Index: 762814 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1060890 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6464. Min Act: -0.0000

Data Index: 489212 (C4 (Web Text))

Max Activating Token Index: 445