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

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

Neuron 4495 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3967. Min Range: -2.3967

Max Act: 2.3967. Min Act: -0.0000

Data Index: 905338 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 2.3967. Min Range: -2.3967

Max Act: 2.1596. Min Act: -0.0000

Data Index: 411897 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 2.3967. Min Range: -2.3967

Max Act: 2.2800. Min Act: -0.0000

Data Index: 1508606 (Python Code)

Max Activating Token Index: 674

Text #3

Max Range: 2.3967. Min Range: -2.3967

Max Act: 2.1839. Min Act: -0.0000

Data Index: 605733 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 2.3967. Min Range: -2.3967

Max Act: 2.1724. Min Act: -0.0000

Data Index: 763557 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 2.3967. Min Range: -2.3967

Max Act: 2.1614. Min Act: -0.0000

Data Index: 881662 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 2.3967. Min Range: -2.3967

Max Act: 1.9420. Min Act: -0.0000

Data Index: 814262 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 2.3967. Min Range: -2.3967

Max Act: 2.0455. Min Act: -0.0000

Data Index: 392913 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 2.3967. Min Range: -2.3967

Max Act: 2.0324. Min Act: -0.0000

Data Index: 776306 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 2.3967. Min Range: -2.3967

Max Act: 2.0245. Min Act: -0.0000

Data Index: 1211353 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 2.3967. Min Range: -2.3967

Max Act: 1.8493. Min Act: -0.0000

Data Index: 1097644 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 2.3967. Min Range: -2.3967

Max Act: 2.0038. Min Act: -0.0000

Data Index: 1166508 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 2.3967. Min Range: -2.3967

Max Act: 2.0065. Min Act: -0.0000

Data Index: 647194 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 2.3967. Min Range: -2.3967

Max Act: 2.0059. Min Act: -0.0000

Data Index: 735904 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 2.3967. Min Range: -2.3967

Max Act: 1.8989. Min Act: -0.0000

Data Index: 518601 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 2.3967. Min Range: -2.3967

Max Act: 1.7687. Min Act: -0.0000

Data Index: 479003 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 2.3967. Min Range: -2.3967

Max Act: 1.9759. Min Act: -0.0000

Data Index: 727969 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 2.3967. Min Range: -2.3967

Max Act: 1.8703. Min Act: -0.0000

Data Index: 293445 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 2.3967. Min Range: -2.3967

Max Act: 2.0872. Min Act: -0.0000

Data Index: 867610 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 2.3967. Min Range: -2.3967

Max Act: 1.9725. Min Act: -0.0000

Data Index: 582599 (C4 (Web Text))

Max Activating Token Index: 258