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

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

Neuron 5502 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2424. Min Act: -0.0001

Data Index: 1529024 (Python Code)

Max Activating Token Index: 268

Text #1

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1612359 (Python Code)

Max Activating Token Index: 658

Text #2

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2107. Min Act: -0.0001

Data Index: 1409213 (Python Code)

Max Activating Token Index: 177

Text #3

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2220. Min Act: -0.0000

Data Index: 1492507 (Python Code)

Max Activating Token Index: 642

Text #4

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2038. Min Act: -0.0001

Data Index: 1571802 (Python Code)

Max Activating Token Index: 784

Text #5

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2195. Min Act: -0.0001

Data Index: 1634471 (Python Code)

Max Activating Token Index: 571

Text #6

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2123. Min Act: -0.0001

Data Index: 1437244 (Python Code)

Max Activating Token Index: 814

Text #7

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1399135 (Python Code)

Max Activating Token Index: 807

Text #8

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2249. Min Act: -0.0001

Data Index: 1591452 (Python Code)

Max Activating Token Index: 760

Text #9

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2050. Min Act: -0.0001

Data Index: 1564241 (Python Code)

Max Activating Token Index: 725

Text #10

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1521481 (Python Code)

Max Activating Token Index: 225

Text #11

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2299. Min Act: -0.0001

Data Index: 1545628 (Python Code)

Max Activating Token Index: 755

Text #12

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2006. Min Act: -0.0001

Data Index: 1413573 (Python Code)

Max Activating Token Index: 842

Text #13

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2181. Min Act: -0.0000

Data Index: 1400972 (Python Code)

Max Activating Token Index: 433

Text #14

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2133. Min Act: -0.0001

Data Index: 1520810 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2029. Min Act: -0.0001

Data Index: 1495750 (Python Code)

Max Activating Token Index: 241

Text #16

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2123. Min Act: -0.0001

Data Index: 1577498 (Python Code)

Max Activating Token Index: 573

Text #17

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2082. Min Act: -0.0001

Data Index: 1635146 (Python Code)

Max Activating Token Index: 391

Text #18

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1478770 (Python Code)

Max Activating Token Index: 988

Text #19

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2067. Min Act: -0.0001

Data Index: 1471028 (Python Code)

Max Activating Token Index: 672