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

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

Neuron 3593 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.5031. Min Act: -0.0000

Data Index: 1377931 (Python Code)

Max Activating Token Index: 463

Text #1

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.4737. Min Act: -0.0000

Data Index: 1509273 (Python Code)

Max Activating Token Index: 133

Text #2

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.4133. Min Act: -0.0000

Data Index: 1652272 (Python Code)

Max Activating Token Index: 905

Text #3

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.3084. Min Act: -0.0000

Data Index: 1495472 (Python Code)

Max Activating Token Index: 71

Text #4

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.2549. Min Act: -0.0000

Data Index: 1640156 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.2406. Min Act: -0.0000

Data Index: 1372050 (Python Code)

Max Activating Token Index: 387

Text #6

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.1870. Min Act: -0.0000

Data Index: 1448444 (Python Code)

Max Activating Token Index: 85

Text #7

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.1323. Min Act: -0.0000

Data Index: 1444753 (Python Code)

Max Activating Token Index: 912

Text #8

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.0979. Min Act: -0.0000

Data Index: 1406457 (Python Code)

Max Activating Token Index: 763

Text #9

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.1665. Min Act: -0.0000

Data Index: 1475140 (Python Code)

Max Activating Token Index: 927

Text #10

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.0545. Min Act: -0.0000

Data Index: 1383458 (Python Code)

Max Activating Token Index: 462

Text #11

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.0844. Min Act: -0.0000

Data Index: 1458032 (Python Code)

Max Activating Token Index: 953

Text #12

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.1512. Min Act: -0.0000

Data Index: 1385339 (Python Code)

Max Activating Token Index: 277

Text #13

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1485091 (Python Code)

Max Activating Token Index: 76

Text #14

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.0966. Min Act: -0.0000

Data Index: 1517212 (Python Code)

Max Activating Token Index: 836

Text #15

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.0973. Min Act: -0.0000

Data Index: 1546221 (Python Code)

Max Activating Token Index: 431

Text #16

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1649810 (Python Code)

Max Activating Token Index: 72

Text #17

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.0572. Min Act: -0.0000

Data Index: 1528838 (Python Code)

Max Activating Token Index: 62

Text #18

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.9469. Min Act: -0.0000

Data Index: 1569961 (Python Code)

Max Activating Token Index: 560

Text #19

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1594999 (Python Code)

Max Activating Token Index: 175