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

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

Neuron 3048 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: 0.2137. Min Range: -0.2137

Max Act: 0.1821. Min Act: -0.0001

Data Index: 1277074 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.2005. Min Act: -0.0000

Data Index: 512136 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.2137. Min Act: -0.0000

Data Index: 769881 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1888. Min Act: -0.0001

Data Index: 129653 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1383571 (Python Code)

Max Activating Token Index: 1013

Text #5

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1647. Min Act: -0.0001

Data Index: 881696 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1210080 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1579. Min Act: -0.0001

Data Index: 943411 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1483. Min Act: -0.0000

Data Index: 209939 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1797. Min Act: -0.0000

Data Index: 344668 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1446. Min Act: -0.0000

Data Index: 1178384 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1478. Min Act: -0.0000

Data Index: 104734 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1435. Min Act: -0.0000

Data Index: 367950 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1412. Min Act: -0.0000

Data Index: 549790 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1523. Min Act: -0.0000

Data Index: 536703 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1418. Min Act: -0.0000

Data Index: 729248 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1029493 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1310026 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1486. Min Act: -0.0000

Data Index: 758454 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1377. Min Act: -0.0001

Data Index: 97172 (C4 (Web Text))

Max Activating Token Index: 544