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

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

Neuron 1729 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.7335. Min Act: -0.0002

Data Index: 1538635 (Python Code)

Max Activating Token Index: 17

Text #1

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6531. Min Act: -0.0002

Data Index: 1529106 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6617. Min Act: -0.0002

Data Index: 1500242 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6426. Min Act: -0.0002

Data Index: 1482962 (Python Code)

Max Activating Token Index: 797

Text #4

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.6012. Min Act: -0.0002

Data Index: 1625591 (Python Code)

Max Activating Token Index: 527

Text #5

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5643. Min Act: -0.0002

Data Index: 1435711 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5761. Min Act: -0.0002

Data Index: 1605993 (Python Code)

Max Activating Token Index: 661

Text #7

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5724. Min Act: -0.0002

Data Index: 1389855 (Python Code)

Max Activating Token Index: 706

Text #8

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5534. Min Act: -0.0002

Data Index: 1496038 (Python Code)

Max Activating Token Index: 699

Text #9

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5391. Min Act: -0.0002

Data Index: 1474225 (Python Code)

Max Activating Token Index: 652

Text #10

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5571. Min Act: -0.0002

Data Index: 1567877 (Python Code)

Max Activating Token Index: 364

Text #11

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5291. Min Act: -0.0002

Data Index: 1606693 (Python Code)

Max Activating Token Index: 337

Text #12

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.4966. Min Act: -0.0002

Data Index: 1422840 (Python Code)

Max Activating Token Index: 7

Text #13

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.4966. Min Act: -0.0002

Data Index: 1544876 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.5020. Min Act: -0.0002

Data Index: 1518544 (Python Code)

Max Activating Token Index: 653

Text #15

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.4922. Min Act: -0.0002

Data Index: 1544264 (Python Code)

Max Activating Token Index: 935

Text #16

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.4879. Min Act: -0.0002

Data Index: 1482889 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.4879. Min Act: -0.0002

Data Index: 1579721 (Python Code)

Max Activating Token Index: 14

Text #18

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.4777. Min Act: -0.0002

Data Index: 1497099 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.7335. Min Range: -0.7335

Max Act: 0.4747. Min Act: -0.0002

Data Index: 1478514 (Python Code)

Max Activating Token Index: 17