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

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

Neuron 5380 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1495227 (Python Code)

Max Activating Token Index: 246

Text #1

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5264. Min Act: -0.0000

Data Index: 1530786 (Python Code)

Max Activating Token Index: 632

Text #2

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4290. Min Act: -0.0000

Data Index: 1388724 (Python Code)

Max Activating Token Index: 268

Text #3

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1614133 (Python Code)

Max Activating Token Index: 45

Text #4

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4512. Min Act: -0.0000

Data Index: 1645320 (Python Code)

Max Activating Token Index: 511

Text #5

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4196. Min Act: -0.0000

Data Index: 1432654 (Python Code)

Max Activating Token Index: 303

Text #6

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1508167 (Python Code)

Max Activating Token Index: 368

Text #7

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1591879 (Python Code)

Max Activating Token Index: 645

Text #8

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4256. Min Act: -0.0000

Data Index: 1600385 (Python Code)

Max Activating Token Index: 305

Text #9

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1452101 (Python Code)

Max Activating Token Index: 940

Text #10

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1638767 (Python Code)

Max Activating Token Index: 311

Text #11

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1465478 (Python Code)

Max Activating Token Index: 119

Text #12

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1429967 (Python Code)

Max Activating Token Index: 577

Text #13

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1566454 (Python Code)

Max Activating Token Index: 520

Text #14

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1567951 (Python Code)

Max Activating Token Index: 123

Text #15

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1467210 (Python Code)

Max Activating Token Index: 245

Text #16

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1394061 (Python Code)

Max Activating Token Index: 434

Text #17

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1511231 (Python Code)

Max Activating Token Index: 356

Text #18

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1383152 (Python Code)

Max Activating Token Index: 526

Text #19

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1616299 (Python Code)

Max Activating Token Index: 701