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

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

Neuron 2000 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.1091. Min Act: -0.0002

Data Index: 124951 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.1051. Min Act: -0.0002

Data Index: 819588 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0927. Min Act: -0.0002

Data Index: 211265 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0875. Min Act: -0.0002

Data Index: 198396 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0916. Min Act: -0.0002

Data Index: 438218 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0887. Min Act: -0.0002

Data Index: 6284 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1109365 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0953. Min Act: -0.0002

Data Index: 711494 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0884. Min Act: -0.0002

Data Index: 607362 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0942. Min Act: -0.0002

Data Index: 481782 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0927. Min Act: -0.0002

Data Index: 427844 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0890. Min Act: -0.0002

Data Index: 591807 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0877. Min Act: -0.0002

Data Index: 300121 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0843. Min Act: -0.0002

Data Index: 972575 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0774. Min Act: -0.0002

Data Index: 455361 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0838. Min Act: -0.0002

Data Index: 162577 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0839. Min Act: -0.0002

Data Index: 351748 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0896. Min Act: -0.0002

Data Index: 488261 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0859. Min Act: -0.0002

Data Index: 658625 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0842. Min Act: -0.0002

Data Index: 765262 (C4 (Web Text))

Max Activating Token Index: 500