Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 159 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1805. Min Act: -0.0001

Data Index: 299481 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1798. Min Act: -0.0001

Data Index: 113351 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1785. Min Act: -0.0001

Data Index: 195215 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1297198 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1575. Min Act: -0.0001

Data Index: 142539 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1509. Min Act: -0.0001

Data Index: 856834 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1698. Min Act: -0.0001

Data Index: 594590 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1390. Min Act: -0.0001

Data Index: 1154876 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1523. Min Act: -0.0001

Data Index: 529616 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1475. Min Act: -0.0001

Data Index: 793440 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1463. Min Act: -0.0001

Data Index: 416640 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1540. Min Act: -0.0001

Data Index: 1608072 (Python Code)

Max Activating Token Index: 404

Text #12

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1374. Min Act: -0.0001

Data Index: 1037295 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1472. Min Act: -0.0001

Data Index: 832869 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1597. Min Act: -0.0001

Data Index: 310665 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1370. Min Act: -0.0001

Data Index: 1207520 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1464. Min Act: -0.0001

Data Index: 879824 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1463. Min Act: -0.0001

Data Index: 991850 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1406. Min Act: -0.0001

Data Index: 1562377 (Python Code)

Max Activating Token Index: 886

Text #19

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1395. Min Act: -0.0001

Data Index: 686415 (C4 (Web Text))

Max Activating Token Index: 1008