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

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

Neuron 2201 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: 0.4718. Min Range: -0.4718

Max Act: 0.4718. Min Act: -0.0000

Data Index: 744345 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.4441. Min Act: -0.0001

Data Index: 1284997 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.4385. Min Act: -0.0000

Data Index: 491167 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.4027. Min Act: -0.0000

Data Index: 973241 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.3948. Min Act: -0.0001

Data Index: 859823 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.3918. Min Act: -0.0001

Data Index: 498732 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.3487. Min Act: -0.0001

Data Index: 726779 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.3797. Min Act: -0.0000

Data Index: 513975 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.3654. Min Act: -0.0001

Data Index: 324811 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.3611. Min Act: -0.0001

Data Index: 976925 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.3676. Min Act: -0.0000

Data Index: 983515 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.3565. Min Act: -0.0001

Data Index: 1076084 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.3157. Min Act: -0.0001

Data Index: 479419 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.3602. Min Act: -0.0001

Data Index: 150893 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.2863. Min Act: -0.0001

Data Index: 437120 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.2964. Min Act: -0.0001

Data Index: 167291 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1185881 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.2857. Min Act: -0.0001

Data Index: 1209956 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.2637. Min Act: -0.0001

Data Index: 436993 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.4718. Min Range: -0.4718

Max Act: 0.2623. Min Act: -0.0001

Data Index: 583838 (C4 (Web Text))

Max Activating Token Index: 185