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

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

Neuron 2408 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6508. Min Act: -0.0001

Data Index: 692926 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.7233. Min Act: -0.0001

Data Index: 80670 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.7002. Min Act: -0.0001

Data Index: 1165960 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.7282. Min Act: -0.0001

Data Index: 1115976 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6765. Min Act: -0.0001

Data Index: 297333 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6787. Min Act: -0.0001

Data Index: 556833 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.5071. Min Act: -0.0001

Data Index: 1326518 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6237. Min Act: -0.0001

Data Index: 529854 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6123. Min Act: -0.0001

Data Index: 158639 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6048. Min Act: -0.0001

Data Index: 1033942 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6515. Min Act: -0.0001

Data Index: 1356981 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.5016. Min Act: -0.0001

Data Index: 743873 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.5751. Min Act: -0.0001

Data Index: 396824 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.5554. Min Act: -0.0001

Data Index: 1279673 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.5966. Min Act: -0.0001

Data Index: 1132210 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6433. Min Act: -0.0001

Data Index: 631605 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.5452. Min Act: -0.0001

Data Index: 1001377 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.6071. Min Act: -0.0001

Data Index: 453366 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.5057. Min Act: -0.0001

Data Index: 30318 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.7282. Min Range: -0.7282

Max Act: 0.7213. Min Act: -0.0001

Data Index: 873971 (C4 (Web Text))

Max Activating Token Index: 642