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

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

Neuron 253 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.7622. Min Act: -0.0000

Data Index: 1506209 (Python Code)

Max Activating Token Index: 708

Text #1

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.8361. Min Act: -0.0000

Data Index: 1628510 (Python Code)

Max Activating Token Index: 138

Text #2

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.7352. Min Act: -0.0000

Data Index: 1600250 (Python Code)

Max Activating Token Index: 517

Text #3

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.8302. Min Act: -0.0000

Data Index: 1595863 (Python Code)

Max Activating Token Index: 867

Text #4

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.8127. Min Act: -0.0000

Data Index: 1547005 (Python Code)

Max Activating Token Index: 464

Text #5

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.7007. Min Act: -0.0000

Data Index: 1488098 (Python Code)

Max Activating Token Index: 131

Text #6

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.7972. Min Act: -0.0000

Data Index: 1566512 (Python Code)

Max Activating Token Index: 183

Text #7

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.7607. Min Act: -0.0000

Data Index: 1416167 (Python Code)

Max Activating Token Index: 149

Text #8

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.7553. Min Act: -0.0000

Data Index: 1474446 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.7440. Min Act: -0.0000

Data Index: 1429128 (Python Code)

Max Activating Token Index: 164

Text #10

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.8336. Min Act: -0.0000

Data Index: 1529722 (Python Code)

Max Activating Token Index: 367

Text #11

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.6460. Min Act: -0.0000

Data Index: 1396452 (Python Code)

Max Activating Token Index: 310

Text #12

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.7275. Min Act: -0.0000

Data Index: 1588084 (Python Code)

Max Activating Token Index: 927

Text #13

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.6924. Min Act: -0.0000

Data Index: 1602609 (Python Code)

Max Activating Token Index: 366

Text #14

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.7895. Min Act: -0.0000

Data Index: 1498368 (Python Code)

Max Activating Token Index: 151

Text #15

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.7407. Min Act: -0.0000

Data Index: 1515051 (Python Code)

Max Activating Token Index: 859

Text #16

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.6432. Min Act: -0.0000

Data Index: 1516713 (Python Code)

Max Activating Token Index: 757

Text #17

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.6788. Min Act: -0.0000

Data Index: 1563606 (Python Code)

Max Activating Token Index: 298

Text #18

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.6702. Min Act: -0.0000

Data Index: 1369083 (Python Code)

Max Activating Token Index: 122

Text #19

Max Range: 1.8361. Min Range: -1.8361

Max Act: 1.6727. Min Act: -0.0000

Data Index: 1599136 (Python Code)

Max Activating Token Index: 31