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

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

Neuron 1227 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1352. Min Range: -1.1352

Max Act: 1.1352. Min Act: -0.0001

Data Index: 1551392 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 1.1352. Min Range: -1.1352

Max Act: 1.0070. Min Act: -0.0001

Data Index: 1368307 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9945. Min Act: -0.0001

Data Index: 1583211 (Python Code)

Max Activating Token Index: 859

Text #3

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9986. Min Act: -0.0001

Data Index: 1500319 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9658. Min Act: -0.0001

Data Index: 1575794 (Python Code)

Max Activating Token Index: 810

Text #5

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9256. Min Act: -0.0001

Data Index: 1492315 (Python Code)

Max Activating Token Index: 336

Text #6

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9187. Min Act: -0.0001

Data Index: 1587445 (Python Code)

Max Activating Token Index: 606

Text #7

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8648. Min Act: -0.0001

Data Index: 1426467 (Python Code)

Max Activating Token Index: 69

Text #8

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8561. Min Act: -0.0001

Data Index: 1532097 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9126. Min Act: -0.0001

Data Index: 1491698 (Python Code)

Max Activating Token Index: 289

Text #10

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8606. Min Act: -0.0001

Data Index: 1530156 (Python Code)

Max Activating Token Index: 434

Text #11

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8844. Min Act: -0.0001

Data Index: 1528381 (Python Code)

Max Activating Token Index: 1008

Text #12

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9322. Min Act: -0.0001

Data Index: 1563097 (Python Code)

Max Activating Token Index: 149

Text #13

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9006. Min Act: -0.0001

Data Index: 1385827 (Python Code)

Max Activating Token Index: 189

Text #14

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8787. Min Act: -0.0001

Data Index: 1558604 (Python Code)

Max Activating Token Index: 886

Text #15

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8668. Min Act: -0.0001

Data Index: 1375208 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8942. Min Act: -0.0001

Data Index: 1626383 (Python Code)

Max Activating Token Index: 665

Text #17

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8323. Min Act: -0.0001

Data Index: 1509650 (Python Code)

Max Activating Token Index: 831

Text #18

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8559. Min Act: -0.0001

Data Index: 1491872 (Python Code)

Max Activating Token Index: 229

Text #19

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8129. Min Act: -0.0001

Data Index: 1550645 (Python Code)

Max Activating Token Index: 74