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

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

Neuron 477 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: 2.5505. Min Range: -2.5505

Max Act: 2.5505. Min Act: -0.0000

Data Index: 1468913 (Python Code)

Max Activating Token Index: 190

Text #1

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.5273. Min Act: -0.0000

Data Index: 1515108 (Python Code)

Max Activating Token Index: 606

Text #2

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.2761. Min Act: -0.0000

Data Index: 1579629 (Python Code)

Max Activating Token Index: 114

Text #3

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.3195. Min Act: -0.0000

Data Index: 1457134 (Python Code)

Max Activating Token Index: 123

Text #4

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.2827. Min Act: -0.0000

Data Index: 1400088 (Python Code)

Max Activating Token Index: 786

Text #5

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.4391. Min Act: -0.0000

Data Index: 1524359 (Python Code)

Max Activating Token Index: 772

Text #6

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.2003. Min Act: -0.0000

Data Index: 1431627 (Python Code)

Max Activating Token Index: 276

Text #7

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.1730. Min Act: -0.0000

Data Index: 1435642 (Python Code)

Max Activating Token Index: 591

Text #8

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.2512. Min Act: -0.0000

Data Index: 1445197 (Python Code)

Max Activating Token Index: 545

Text #9

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.1848. Min Act: -0.0000

Data Index: 1573600 (Python Code)

Max Activating Token Index: 462

Text #10

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.2959. Min Act: -0.0000

Data Index: 1365318 (Python Code)

Max Activating Token Index: 616

Text #11

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.1587. Min Act: -0.0000

Data Index: 1416260 (Python Code)

Max Activating Token Index: 316

Text #12

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.1642. Min Act: -0.0000

Data Index: 1629390 (Python Code)

Max Activating Token Index: 234

Text #13

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.1394. Min Act: -0.0000

Data Index: 1416626 (Python Code)

Max Activating Token Index: 513

Text #14

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.2373. Min Act: -0.0000

Data Index: 1537884 (Python Code)

Max Activating Token Index: 512

Text #15

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.1799. Min Act: -0.0000

Data Index: 1553902 (Python Code)

Max Activating Token Index: 866

Text #16

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.1133. Min Act: -0.0000

Data Index: 1471772 (Python Code)

Max Activating Token Index: 478

Text #17

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.2082. Min Act: -0.0000

Data Index: 1518047 (Python Code)

Max Activating Token Index: 938

Text #18

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.1599. Min Act: -0.0000

Data Index: 1615497 (Python Code)

Max Activating Token Index: 100

Text #19

Max Range: 2.5505. Min Range: -2.5505

Max Act: 2.1126. Min Act: -0.0000

Data Index: 1376938 (Python Code)

Max Activating Token Index: 684