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

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

Neuron 3706 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1290. Min Act: -0.0001

Data Index: 566020 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1236. Min Act: -0.0001

Data Index: 603667 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1218. Min Act: -0.0001

Data Index: 895890 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1177871 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1131. Min Act: -0.0001

Data Index: 607822 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0987. Min Act: -0.0001

Data Index: 111321 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1044. Min Act: -0.0001

Data Index: 885182 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1059. Min Act: -0.0001

Data Index: 550249 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0941. Min Act: -0.0001

Data Index: 45239 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0988. Min Act: -0.0001

Data Index: 313591 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1276774 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0996. Min Act: -0.0001

Data Index: 576100 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0911. Min Act: -0.0001

Data Index: 851774 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0975. Min Act: -0.0001

Data Index: 100309 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1198611 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0900. Min Act: -0.0001

Data Index: 466569 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0855. Min Act: -0.0001

Data Index: 738661 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0888. Min Act: -0.0001

Data Index: 823007 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0845. Min Act: -0.0001

Data Index: 406438 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0881. Min Act: -0.0001

Data Index: 110303 (C4 (Web Text))

Max Activating Token Index: 557