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

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

Neuron 3733 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.6062. Min Act: -0.0001

Data Index: 690044 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5653. Min Act: -0.0001

Data Index: 741185 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4903. Min Act: -0.0001

Data Index: 276016 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4631. Min Act: -0.0001

Data Index: 1199279 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4645. Min Act: -0.0001

Data Index: 245268 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4883. Min Act: -0.0001

Data Index: 1072679 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4559. Min Act: -0.0001

Data Index: 298001 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4313. Min Act: -0.0001

Data Index: 40519 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4706. Min Act: -0.0001

Data Index: 447346 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4231. Min Act: -0.0001

Data Index: 75013 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4526. Min Act: -0.0001

Data Index: 188116 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4455. Min Act: -0.0001

Data Index: 621504 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4440. Min Act: -0.0001

Data Index: 31142 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4422. Min Act: -0.0001

Data Index: 1003822 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4049. Min Act: -0.0001

Data Index: 214711 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4168. Min Act: -0.0001

Data Index: 24146 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4556. Min Act: -0.0001

Data Index: 444733 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4590. Min Act: -0.0001

Data Index: 710476 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4246. Min Act: -0.0001

Data Index: 699016 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4086. Min Act: -0.0001

Data Index: 1063000 (C4 (Web Text))

Max Activating Token Index: 897