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

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

Neuron 389 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1465032 (Python Code)

Max Activating Token Index: 141

Text #1

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1027989 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1389237 (Python Code)

Max Activating Token Index: 44

Text #3

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0210. Min Act: -0.0002

Data Index: 560852 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1436526 (Python Code)

Max Activating Token Index: 98

Text #5

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0209. Min Act: -0.0002

Data Index: 105458 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1401965 (Python Code)

Max Activating Token Index: 761

Text #7

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0206. Min Act: -0.0002

Data Index: 857925 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0206. Min Act: -0.0002

Data Index: 21458 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0205. Min Act: -0.0001

Data Index: 634403 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1472113 (Python Code)

Max Activating Token Index: 143

Text #11

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1638238 (Python Code)

Max Activating Token Index: 346

Text #12

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1251373 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0203. Min Act: -0.0002

Data Index: 177250 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1407614 (Python Code)

Max Activating Token Index: 177

Text #15

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1573235 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1496980 (Python Code)

Max Activating Token Index: 43

Text #17

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1637199 (Python Code)

Max Activating Token Index: 945

Text #18

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1031777 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0199. Min Act: -0.0002

Data Index: 869851 (C4 (Web Text))

Max Activating Token Index: 510