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

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

Neuron 3387 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.6389. Min Act: -0.0000

Data Index: 578182 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4801. Min Act: -0.0000

Data Index: 454833 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5010. Min Act: -0.0000

Data Index: 292565 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1032323 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4295. Min Act: -0.0000

Data Index: 541397 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.3830. Min Act: -0.0000

Data Index: 944639 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4041. Min Act: -0.0000

Data Index: 816806 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1320166 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4037. Min Act: -0.0000

Data Index: 245736 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.3964. Min Act: -0.0000

Data Index: 135332 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1298524 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.3665. Min Act: -0.0000

Data Index: 826136 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.3648. Min Act: -0.0000

Data Index: 751549 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.3779. Min Act: -0.0000

Data Index: 537394 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.3761. Min Act: -0.0000

Data Index: 696321 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.3872. Min Act: -0.0000

Data Index: 988928 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.3873. Min Act: -0.0000

Data Index: 725469 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.3769. Min Act: -0.0000

Data Index: 403829 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.3592. Min Act: -0.0000

Data Index: 90562 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.3615. Min Act: -0.0000

Data Index: 49516 (C4 (Web Text))

Max Activating Token Index: 749