Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 94 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.4780. Min Act: -0.0006

Data Index: 777441 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.4222. Min Act: -0.0006

Data Index: 127827 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.4136. Min Act: -0.0006

Data Index: 567382 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3857. Min Act: -0.0006

Data Index: 1163267 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.4038. Min Act: -0.0006

Data Index: 446445 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3859. Min Act: -0.0006

Data Index: 1256465 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3929. Min Act: -0.0006

Data Index: 249381 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3895. Min Act: -0.0006

Data Index: 307707 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3883. Min Act: -0.0006

Data Index: 361638 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3979. Min Act: -0.0006

Data Index: 634477 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3853. Min Act: -0.0006

Data Index: 877930 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3716. Min Act: -0.0006

Data Index: 814154 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3792. Min Act: -0.0006

Data Index: 381851 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3604. Min Act: -0.0006

Data Index: 166338 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3880. Min Act: -0.0006

Data Index: 122635 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3748. Min Act: -0.0006

Data Index: 898875 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3741. Min Act: -0.0006

Data Index: 177443 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3855. Min Act: -0.0006

Data Index: 854178 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3851. Min Act: -0.0006

Data Index: 455414 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3588. Min Act: -0.0006

Data Index: 1134996 (C4 (Web Text))

Max Activating Token Index: 181