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

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

Neuron 1196 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: 3.3745. Min Range: -3.3745

Max Act: 3.3745. Min Act: -0.0000

Data Index: 1442113 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 3.3745. Min Range: -3.3745

Max Act: 3.3358. Min Act: -0.0000

Data Index: 1505110 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 3.3745. Min Range: -3.3745

Max Act: 3.0427. Min Act: -0.0000

Data Index: 1434432 (Python Code)

Max Activating Token Index: 113

Text #3

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.8100. Min Act: -0.0000

Data Index: 1430268 (Python Code)

Max Activating Token Index: 597

Text #4

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.7470. Min Act: -0.0000

Data Index: 1588570 (Python Code)

Max Activating Token Index: 795

Text #5

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.8366. Min Act: -0.0000

Data Index: 318686 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.5298. Min Act: -0.0000

Data Index: 1554081 (Python Code)

Max Activating Token Index: 590

Text #7

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.6464. Min Act: -0.0000

Data Index: 1589583 (Python Code)

Max Activating Token Index: 461

Text #8

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.6246. Min Act: -0.0000

Data Index: 1584939 (Python Code)

Max Activating Token Index: 591

Text #9

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.5495. Min Act: -0.0000

Data Index: 1652366 (Python Code)

Max Activating Token Index: 710

Text #10

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.5642. Min Act: -0.0000

Data Index: 1293742 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.6853. Min Act: -0.0000

Data Index: 1418283 (Python Code)

Max Activating Token Index: 180

Text #12

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.5433. Min Act: -0.0000

Data Index: 1611572 (Python Code)

Max Activating Token Index: 980

Text #13

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.5163. Min Act: -0.0000

Data Index: 26062 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.5315. Min Act: -0.0000

Data Index: 1445341 (Python Code)

Max Activating Token Index: 851

Text #15

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.3657. Min Act: -0.0000

Data Index: 1326376 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.1509. Min Act: -0.0000

Data Index: 1552978 (Python Code)

Max Activating Token Index: 806

Text #17

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.7303. Min Act: -0.0000

Data Index: 862164 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.4405. Min Act: -0.0000

Data Index: 480984 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 3.3745. Min Range: -3.3745

Max Act: 2.2838. Min Act: -0.0000

Data Index: 987591 (C4 (Web Text))

Max Activating Token Index: 856