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

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

Neuron 4997 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.7302. Min Act: -0.0001

Data Index: 1588403 (Python Code)

Max Activating Token Index: 113

Text #1

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.7432. Min Act: -0.0001

Data Index: 1530834 (Python Code)

Max Activating Token Index: 79

Text #2

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6898. Min Act: -0.0001

Data Index: 1527671 (Python Code)

Max Activating Token Index: 504

Text #3

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6847. Min Act: -0.0001

Data Index: 1517536 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6955. Min Act: -0.0001

Data Index: 1655458 (Python Code)

Max Activating Token Index: 93

Text #5

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6444. Min Act: -0.0001

Data Index: 1392387 (Python Code)

Max Activating Token Index: 173

Text #6

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6281. Min Act: -0.0001

Data Index: 1430472 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6209. Min Act: -0.0001

Data Index: 1479665 (Python Code)

Max Activating Token Index: 321

Text #8

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6435. Min Act: -0.0001

Data Index: 1521980 (Python Code)

Max Activating Token Index: 311

Text #9

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6232. Min Act: -0.0001

Data Index: 1589237 (Python Code)

Max Activating Token Index: 197

Text #10

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6199. Min Act: -0.0001

Data Index: 1526646 (Python Code)

Max Activating Token Index: 131

Text #11

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6799. Min Act: -0.0001

Data Index: 1497329 (Python Code)

Max Activating Token Index: 152

Text #12

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5767. Min Act: -0.0001

Data Index: 1465657 (Python Code)

Max Activating Token Index: 205

Text #13

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6370. Min Act: -0.0001

Data Index: 1430545 (Python Code)

Max Activating Token Index: 613

Text #14

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6317. Min Act: -0.0001

Data Index: 1582642 (Python Code)

Max Activating Token Index: 255

Text #15

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6299. Min Act: -0.0001

Data Index: 1488380 (Python Code)

Max Activating Token Index: 93

Text #16

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6188. Min Act: -0.0001

Data Index: 1523436 (Python Code)

Max Activating Token Index: 670

Text #17

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6458. Min Act: -0.0001

Data Index: 1621628 (Python Code)

Max Activating Token Index: 404

Text #18

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6031. Min Act: -0.0001

Data Index: 1525495 (Python Code)

Max Activating Token Index: 603

Text #19

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5776. Min Act: -0.0001

Data Index: 1653738 (Python Code)

Max Activating Token Index: 159