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

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

Neuron 3986 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: 5.5240. Min Range: -5.5240

Max Act: 5.5240. Min Act: -0.0000

Data Index: 1400550 (Python Code)

Max Activating Token Index: 586

Text #1

Max Range: 5.5240. Min Range: -5.5240

Max Act: 5.0916. Min Act: -0.0000

Data Index: 1559300 (Python Code)

Max Activating Token Index: 751

Text #2

Max Range: 5.5240. Min Range: -5.5240

Max Act: 5.4712. Min Act: -0.0000

Data Index: 1394141 (Python Code)

Max Activating Token Index: 945

Text #3

Max Range: 5.5240. Min Range: -5.5240

Max Act: 5.2883. Min Act: -0.0000

Data Index: 1551214 (Python Code)

Max Activating Token Index: 464

Text #4

Max Range: 5.5240. Min Range: -5.5240

Max Act: 4.7874. Min Act: -0.0000

Data Index: 1374491 (Python Code)

Max Activating Token Index: 957

Text #5

Max Range: 5.5240. Min Range: -5.5240

Max Act: 5.3041. Min Act: -0.0000

Data Index: 1637157 (Python Code)

Max Activating Token Index: 820

Text #6

Max Range: 5.5240. Min Range: -5.5240

Max Act: 4.9577. Min Act: -0.0000

Data Index: 1506440 (Python Code)

Max Activating Token Index: 802

Text #7

Max Range: 5.5240. Min Range: -5.5240

Max Act: 5.3153. Min Act: -0.0000

Data Index: 1461178 (Python Code)

Max Activating Token Index: 363

Text #8

Max Range: 5.5240. Min Range: -5.5240

Max Act: 4.8711. Min Act: -0.0000

Data Index: 1517848 (Python Code)

Max Activating Token Index: 182

Text #9

Max Range: 5.5240. Min Range: -5.5240

Max Act: 5.2206. Min Act: -0.0000

Data Index: 1399721 (Python Code)

Max Activating Token Index: 445

Text #10

Max Range: 5.5240. Min Range: -5.5240

Max Act: 4.8458. Min Act: -0.0000

Data Index: 1414528 (Python Code)

Max Activating Token Index: 547

Text #11

Max Range: 5.5240. Min Range: -5.5240

Max Act: 4.8541. Min Act: -0.0000

Data Index: 1596371 (Python Code)

Max Activating Token Index: 271

Text #12

Max Range: 5.5240. Min Range: -5.5240

Max Act: 4.8485. Min Act: -0.0000

Data Index: 1576602 (Python Code)

Max Activating Token Index: 136

Text #13

Max Range: 5.5240. Min Range: -5.5240

Max Act: 5.0087. Min Act: -0.0000

Data Index: 1565254 (Python Code)

Max Activating Token Index: 734

Text #14

Max Range: 5.5240. Min Range: -5.5240

Max Act: 5.1658. Min Act: -0.0000

Data Index: 1425064 (Python Code)

Max Activating Token Index: 914

Text #15

Max Range: 5.5240. Min Range: -5.5240

Max Act: 4.9867. Min Act: -0.0000

Data Index: 1503453 (Python Code)

Max Activating Token Index: 33

Text #16

Max Range: 5.5240. Min Range: -5.5240

Max Act: 4.9867. Min Act: -0.0000

Data Index: 1448615 (Python Code)

Max Activating Token Index: 33

Text #17

Max Range: 5.5240. Min Range: -5.5240

Max Act: 4.9784. Min Act: -0.0000

Data Index: 1509571 (Python Code)

Max Activating Token Index: 752

Text #18

Max Range: 5.5240. Min Range: -5.5240

Max Act: 4.9597. Min Act: -0.0000

Data Index: 1578815 (Python Code)

Max Activating Token Index: 541

Text #19

Max Range: 5.5240. Min Range: -5.5240

Max Act: 4.9506. Min Act: -0.0000

Data Index: 1615007 (Python Code)

Max Activating Token Index: 489