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

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

Neuron 1946 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.9039. Min Act: -0.0000

Data Index: 1640454 (Python Code)

Max Activating Token Index: 136

Text #1

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.7741. Min Act: -0.0000

Data Index: 1379618 (Python Code)

Max Activating Token Index: 273

Text #2

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.3652. Min Act: -0.0000

Data Index: 1519258 (Python Code)

Max Activating Token Index: 76

Text #3

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.6124. Min Act: -0.0000

Data Index: 1506574 (Python Code)

Max Activating Token Index: 112

Text #4

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.4256. Min Act: -0.0000

Data Index: 1599136 (Python Code)

Max Activating Token Index: 270

Text #5

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.2223. Min Act: -0.0000

Data Index: 1373463 (Python Code)

Max Activating Token Index: 899

Text #6

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.4480. Min Act: -0.0000

Data Index: 1440255 (Python Code)

Max Activating Token Index: 603

Text #7

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.3318. Min Act: -0.0000

Data Index: 1368608 (Python Code)

Max Activating Token Index: 846

Text #8

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.2799. Min Act: -0.0000

Data Index: 1608618 (Python Code)

Max Activating Token Index: 916

Text #9

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.2544. Min Act: -0.0000

Data Index: 1380356 (Python Code)

Max Activating Token Index: 303

Text #10

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.0864. Min Act: -0.0000

Data Index: 1470555 (Python Code)

Max Activating Token Index: 788

Text #11

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.3186. Min Act: -0.0000

Data Index: 1433227 (Python Code)

Max Activating Token Index: 916

Text #12

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.1581. Min Act: -0.0000

Data Index: 1377950 (Python Code)

Max Activating Token Index: 529

Text #13

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.2360. Min Act: -0.0000

Data Index: 1421890 (Python Code)

Max Activating Token Index: 822

Text #14

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.1013. Min Act: -0.0000

Data Index: 1562660 (Python Code)

Max Activating Token Index: 221

Text #15

Max Range: 2.9039. Min Range: -2.9039

Max Act: 1.9291. Min Act: -0.0000

Data Index: 1504601 (Python Code)

Max Activating Token Index: 761

Text #16

Max Range: 2.9039. Min Range: -2.9039

Max Act: 1.8186. Min Act: -0.0000

Data Index: 1366923 (Python Code)

Max Activating Token Index: 870

Text #17

Max Range: 2.9039. Min Range: -2.9039

Max Act: 1.9157. Min Act: -0.0000

Data Index: 1598008 (Python Code)

Max Activating Token Index: 1014

Text #18

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.0262. Min Act: -0.0000

Data Index: 1633049 (Python Code)

Max Activating Token Index: 415

Text #19

Max Range: 2.9039. Min Range: -2.9039

Max Act: 2.0001. Min Act: -0.0000

Data Index: 1629969 (Python Code)

Max Activating Token Index: 265