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

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

Neuron 3525 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6465. Min Range: -4.6465

Max Act: 4.6465. Min Act: -0.0000

Data Index: 1375223 (Python Code)

Max Activating Token Index: 462

Text #1

Max Range: 4.6465. Min Range: -4.6465

Max Act: 3.6108. Min Act: -0.0000

Data Index: 1394335 (Python Code)

Max Activating Token Index: 835

Text #2

Max Range: 4.6465. Min Range: -4.6465

Max Act: 2.5915. Min Act: -0.0000

Data Index: 1600214 (Python Code)

Max Activating Token Index: 648

Text #3

Max Range: 4.6465. Min Range: -4.6465

Max Act: 2.2807. Min Act: -0.0000

Data Index: 1617497 (Python Code)

Max Activating Token Index: 305

Text #4

Max Range: 4.6465. Min Range: -4.6465

Max Act: 2.3551. Min Act: -0.0000

Data Index: 1554081 (Python Code)

Max Activating Token Index: 235

Text #5

Max Range: 4.6465. Min Range: -4.6465

Max Act: 2.1889. Min Act: -0.0000

Data Index: 1526935 (Python Code)

Max Activating Token Index: 252

Text #6

Max Range: 4.6465. Min Range: -4.6465

Max Act: 2.3150. Min Act: -0.0000

Data Index: 1562827 (Python Code)

Max Activating Token Index: 852

Text #7

Max Range: 4.6465. Min Range: -4.6465

Max Act: 2.1959. Min Act: -0.0000

Data Index: 1543481 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 4.6465. Min Range: -4.6465

Max Act: 2.2450. Min Act: -0.0000

Data Index: 1443295 (Python Code)

Max Activating Token Index: 124

Text #9

Max Range: 4.6465. Min Range: -4.6465

Max Act: 2.0312. Min Act: -0.0000

Data Index: 1615372 (Python Code)

Max Activating Token Index: 802

Text #10

Max Range: 4.6465. Min Range: -4.6465

Max Act: 1.9919. Min Act: -0.0000

Data Index: 1363077 (Python Code)

Max Activating Token Index: 747

Text #11

Max Range: 4.6465. Min Range: -4.6465

Max Act: 2.0771. Min Act: -0.0000

Data Index: 1520771 (Python Code)

Max Activating Token Index: 187

Text #12

Max Range: 4.6465. Min Range: -4.6465

Max Act: 2.0326. Min Act: -0.0000

Data Index: 1490831 (Python Code)

Max Activating Token Index: 348

Text #13

Max Range: 4.6465. Min Range: -4.6465

Max Act: 1.8718. Min Act: -0.0000

Data Index: 1577183 (Python Code)

Max Activating Token Index: 766

Text #14

Max Range: 4.6465. Min Range: -4.6465

Max Act: 1.9353. Min Act: -0.0000

Data Index: 1365650 (Python Code)

Max Activating Token Index: 697

Text #15

Max Range: 4.6465. Min Range: -4.6465

Max Act: 2.0110. Min Act: -0.0000

Data Index: 1627384 (Python Code)

Max Activating Token Index: 742

Text #16

Max Range: 4.6465. Min Range: -4.6465

Max Act: 1.9379. Min Act: -0.0000

Data Index: 1405954 (Python Code)

Max Activating Token Index: 335

Text #17

Max Range: 4.6465. Min Range: -4.6465

Max Act: 1.9217. Min Act: -0.0000

Data Index: 1486825 (Python Code)

Max Activating Token Index: 829

Text #18

Max Range: 4.6465. Min Range: -4.6465

Max Act: 1.9955. Min Act: -0.0000

Data Index: 1618717 (Python Code)

Max Activating Token Index: 133

Text #19

Max Range: 4.6465. Min Range: -4.6465

Max Act: 2.0396. Min Act: -0.0000

Data Index: 1424169 (Python Code)

Max Activating Token Index: 333