Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 260 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5875. Min Act: -0.0000

Data Index: 405938 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4705. Min Act: -0.0000

Data Index: 845093 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4534. Min Act: -0.0001

Data Index: 654509 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1032771 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4760. Min Act: -0.0000

Data Index: 407407 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4366. Min Act: -0.0001

Data Index: 870478 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4298. Min Act: -0.0001

Data Index: 900389 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4314. Min Act: -0.0000

Data Index: 758121 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3902. Min Act: -0.0001

Data Index: 1108420 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4051. Min Act: -0.0000

Data Index: 687828 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3941. Min Act: -0.0001

Data Index: 646440 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3781. Min Act: -0.0000

Data Index: 15673 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4029. Min Act: -0.0001

Data Index: 849820 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3792. Min Act: -0.0001

Data Index: 1150233 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3680. Min Act: -0.0001

Data Index: 646149 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3869. Min Act: -0.0000

Data Index: 122294 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3747. Min Act: -0.0001

Data Index: 1098327 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3611. Min Act: -0.0000

Data Index: 349196 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3707. Min Act: -0.0000

Data Index: 728859 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3658. Min Act: -0.0000

Data Index: 690907 (C4 (Web Text))

Max Activating Token Index: 43