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

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

Neuron 944 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: 1.8804. Min Range: -1.8804

Max Act: 1.8804. Min Act: -0.0000

Data Index: 1630029 (Python Code)

Max Activating Token Index: 351

Text #1

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.6730. Min Act: -0.0000

Data Index: 1499440 (Python Code)

Max Activating Token Index: 61

Text #2

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.5817. Min Act: -0.0000

Data Index: 1453888 (Python Code)

Max Activating Token Index: 726

Text #3

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.5859. Min Act: -0.0000

Data Index: 1646396 (Python Code)

Max Activating Token Index: 400

Text #4

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.6629. Min Act: -0.0000

Data Index: 1525839 (Python Code)

Max Activating Token Index: 663

Text #5

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.5205. Min Act: -0.0000

Data Index: 1438520 (Python Code)

Max Activating Token Index: 913

Text #6

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.4161. Min Act: -0.0000

Data Index: 1574006 (Python Code)

Max Activating Token Index: 955

Text #7

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.3213. Min Act: -0.0000

Data Index: 1505236 (Python Code)

Max Activating Token Index: 369

Text #8

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.3728. Min Act: -0.0000

Data Index: 1625826 (Python Code)

Max Activating Token Index: 362

Text #9

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.3739. Min Act: -0.0000

Data Index: 1377354 (Python Code)

Max Activating Token Index: 873

Text #10

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.2168. Min Act: -0.0000

Data Index: 1511527 (Python Code)

Max Activating Token Index: 500

Text #11

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.2030. Min Act: -0.0000

Data Index: 1427467 (Python Code)

Max Activating Token Index: 750

Text #12

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.1530. Min Act: -0.0000

Data Index: 1655632 (Python Code)

Max Activating Token Index: 511

Text #13

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.1942. Min Act: -0.0000

Data Index: 1442269 (Python Code)

Max Activating Token Index: 751

Text #14

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.2170. Min Act: -0.0000

Data Index: 1579602 (Python Code)

Max Activating Token Index: 729

Text #15

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.2933. Min Act: -0.0000

Data Index: 1593814 (Python Code)

Max Activating Token Index: 673

Text #16

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.1799. Min Act: -0.0000

Data Index: 1466943 (Python Code)

Max Activating Token Index: 904

Text #17

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.1797. Min Act: -0.0000

Data Index: 1442079 (Python Code)

Max Activating Token Index: 887

Text #18

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.1796. Min Act: -0.0000

Data Index: 1628454 (Python Code)

Max Activating Token Index: 453

Text #19

Max Range: 1.8804. Min Range: -1.8804

Max Act: 1.1637. Min Act: -0.0000

Data Index: 1587293 (Python Code)

Max Activating Token Index: 419