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

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

Neuron 4046 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: 6.4985. Min Range: -6.4985

Max Act: 6.4985. Min Act: -0.0000

Data Index: 1622363 (Python Code)

Max Activating Token Index: 78

Text #1

Max Range: 6.4985. Min Range: -6.4985

Max Act: 6.2845. Min Act: -0.0000

Data Index: 1497599 (Python Code)

Max Activating Token Index: 854

Text #2

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.9147. Min Act: -0.0000

Data Index: 1581917 (Python Code)

Max Activating Token Index: 740

Text #3

Max Range: 6.4985. Min Range: -6.4985

Max Act: 6.1298. Min Act: -0.0000

Data Index: 1583937 (Python Code)

Max Activating Token Index: 112

Text #4

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.5432. Min Act: -0.0000

Data Index: 1605514 (Python Code)

Max Activating Token Index: 841

Text #5

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.8596. Min Act: -0.0000

Data Index: 1511717 (Python Code)

Max Activating Token Index: 954

Text #6

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.8672. Min Act: -0.0000

Data Index: 1564971 (Python Code)

Max Activating Token Index: 897

Text #7

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.9581. Min Act: -0.0000

Data Index: 1563515 (Python Code)

Max Activating Token Index: 677

Text #8

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.9327. Min Act: -0.0000

Data Index: 1484645 (Python Code)

Max Activating Token Index: 620

Text #9

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.7339. Min Act: -0.0000

Data Index: 1591667 (Python Code)

Max Activating Token Index: 716

Text #10

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.9517. Min Act: -0.0000

Data Index: 1582284 (Python Code)

Max Activating Token Index: 801

Text #11

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.5485. Min Act: -0.0000

Data Index: 1565917 (Python Code)

Max Activating Token Index: 182

Text #12

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.6973. Min Act: -0.0000

Data Index: 1652333 (Python Code)

Max Activating Token Index: 745

Text #13

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.8768. Min Act: -0.0000

Data Index: 1386372 (Python Code)

Max Activating Token Index: 1006

Text #14

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.8887. Min Act: -0.0000

Data Index: 1420992 (Python Code)

Max Activating Token Index: 987

Text #15

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.8374. Min Act: -0.0000

Data Index: 1464312 (Python Code)

Max Activating Token Index: 981

Text #16

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.6620. Min Act: -0.0000

Data Index: 1511712 (Python Code)

Max Activating Token Index: 819

Text #17

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.4782. Min Act: -0.0000

Data Index: 1448290 (Python Code)

Max Activating Token Index: 836

Text #18

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.8226. Min Act: -0.0000

Data Index: 1368053 (Python Code)

Max Activating Token Index: 935

Text #19

Max Range: 6.4985. Min Range: -6.4985

Max Act: 5.6162. Min Act: -0.0000

Data Index: 1537662 (Python Code)

Max Activating Token Index: 437