Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2171 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.9303. Min Act: 0.0000

Data Index: 1427927 (Python Code)

Max Activating Token Index: 149

Text #1

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.8113. Min Act: 0.0001

Data Index: 1523195 (Python Code)

Max Activating Token Index: 426

Text #2

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.7468. Min Act: 0.0001

Data Index: 1585454 (Python Code)

Max Activating Token Index: 598

Text #3

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6404. Min Act: 0.0000

Data Index: 1433062 (Python Code)

Max Activating Token Index: 745

Text #4

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6538. Min Act: 0.0001

Data Index: 1512935 (Python Code)

Max Activating Token Index: 457

Text #5

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6509. Min Act: 0.0001

Data Index: 1479774 (Python Code)

Max Activating Token Index: 489

Text #6

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6559. Min Act: 0.0001

Data Index: 1434966 (Python Code)

Max Activating Token Index: 777

Text #7

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6906. Min Act: 0.0001

Data Index: 1458128 (Python Code)

Max Activating Token Index: 655

Text #8

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6133. Min Act: 0.0001

Data Index: 1568123 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1511655 (Python Code)

Max Activating Token Index: 780

Text #10

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.5790. Min Act: 0.0001

Data Index: 1421690 (Python Code)

Max Activating Token Index: 986

Text #11

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.5698. Min Act: 0.0001

Data Index: 1547726 (Python Code)

Max Activating Token Index: 927

Text #12

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1473793 (Python Code)

Max Activating Token Index: 961

Text #13

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.5413. Min Act: 0.0000

Data Index: 1387158 (Python Code)

Max Activating Token Index: 26

Text #14

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.5754. Min Act: 0.0001

Data Index: 1514014 (Python Code)

Max Activating Token Index: 131

Text #15

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.5481. Min Act: 0.0001

Data Index: 1493036 (Python Code)

Max Activating Token Index: 108

Text #16

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1630923 (Python Code)

Max Activating Token Index: 860

Text #17

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.5301. Min Act: 0.0000

Data Index: 1526904 (Python Code)

Max Activating Token Index: 74

Text #18

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.5854. Min Act: 0.0001

Data Index: 1380828 (Python Code)

Max Activating Token Index: 640

Text #19

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.5575. Min Act: 0.0000

Data Index: 1581051 (Python Code)

Max Activating Token Index: 238