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

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

Neuron 3671 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5963. Min Range: -1.5963

Max Act: 1.5963. Min Act: 0.0001

Data Index: 1467003 (Python Code)

Max Activating Token Index: 33

Text #1

Max Range: 1.5963. Min Range: -1.5963

Max Act: 1.4224. Min Act: 0.0001

Data Index: 1588869 (Python Code)

Max Activating Token Index: 56

Text #2

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.9546. Min Act: 0.0000

Data Index: 1631116 (Python Code)

Max Activating Token Index: 356

Text #3

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1122439 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1232804 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.6446. Min Act: 0.0001

Data Index: 1428385 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.6028. Min Act: 0.0001

Data Index: 1621586 (Python Code)

Max Activating Token Index: 276

Text #7

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.6207. Min Act: -0.0000

Data Index: 886767 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.6268. Min Act: 0.0001

Data Index: 1608127 (Python Code)

Max Activating Token Index: 904

Text #9

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.6164. Min Act: -0.0000

Data Index: 306420 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.5766. Min Act: 0.0001

Data Index: 1519254 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.6141. Min Act: 0.0001

Data Index: 1586701 (Python Code)

Max Activating Token Index: 541

Text #12

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1300903 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1563485 (Python Code)

Max Activating Token Index: 544

Text #14

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1412517 (Python Code)

Max Activating Token Index: 285

Text #15

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.5944. Min Act: 0.0001

Data Index: 1384866 (Python Code)

Max Activating Token Index: 992

Text #16

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.5769. Min Act: 0.0001

Data Index: 1540484 (Python Code)

Max Activating Token Index: 837

Text #17

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.5588. Min Act: -0.0000

Data Index: 637869 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.5638. Min Act: 0.0001

Data Index: 1394315 (Python Code)

Max Activating Token Index: 47

Text #19

Max Range: 1.5963. Min Range: -1.5963

Max Act: 0.5611. Min Act: 0.0001

Data Index: 1581677 (Python Code)

Max Activating Token Index: 75