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

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

Neuron 2113 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: 2.0008. Min Range: -2.0008

Max Act: 2.0008. Min Act: -0.0000

Data Index: 1587899 (Python Code)

Max Activating Token Index: 746

Text #1

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.9375. Min Act: -0.0000

Data Index: 1605771 (Python Code)

Max Activating Token Index: 761

Text #2

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.8881. Min Act: -0.0000

Data Index: 1485918 (Python Code)

Max Activating Token Index: 975

Text #3

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.8892. Min Act: -0.0000

Data Index: 1533441 (Python Code)

Max Activating Token Index: 656

Text #4

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.8825. Min Act: -0.0000

Data Index: 1382904 (Python Code)

Max Activating Token Index: 148

Text #5

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.8266. Min Act: -0.0000

Data Index: 1608731 (Python Code)

Max Activating Token Index: 306

Text #6

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.7610. Min Act: -0.0000

Data Index: 1465653 (Python Code)

Max Activating Token Index: 494

Text #7

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.7908. Min Act: -0.0000

Data Index: 1477073 (Python Code)

Max Activating Token Index: 353

Text #8

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.8138. Min Act: -0.0000

Data Index: 1389655 (Python Code)

Max Activating Token Index: 171

Text #9

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.7809. Min Act: -0.0000

Data Index: 1362141 (Python Code)

Max Activating Token Index: 628

Text #10

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.6568. Min Act: -0.0000

Data Index: 1625921 (Python Code)

Max Activating Token Index: 345

Text #11

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.7349. Min Act: -0.0000

Data Index: 1578977 (Python Code)

Max Activating Token Index: 847

Text #12

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.7460. Min Act: -0.0000

Data Index: 1613520 (Python Code)

Max Activating Token Index: 216

Text #13

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.7315. Min Act: -0.0000

Data Index: 1499505 (Python Code)

Max Activating Token Index: 170

Text #14

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.7012. Min Act: -0.0000

Data Index: 1553274 (Python Code)

Max Activating Token Index: 252

Text #15

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.6472. Min Act: -0.0000

Data Index: 1631852 (Python Code)

Max Activating Token Index: 414

Text #16

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.6301. Min Act: -0.0000

Data Index: 1632252 (Python Code)

Max Activating Token Index: 349

Text #17

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.7573. Min Act: -0.0000

Data Index: 1443035 (Python Code)

Max Activating Token Index: 831

Text #18

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.5953. Min Act: -0.0000

Data Index: 1574437 (Python Code)

Max Activating Token Index: 742

Text #19

Max Range: 2.0008. Min Range: -2.0008

Max Act: 1.5806. Min Act: -0.0000

Data Index: 1409178 (Python Code)

Max Activating Token Index: 631