Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 892 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0889. Min Act: -0.0006

Data Index: 139436 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0870. Min Act: -0.0006

Data Index: 30741 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0867. Min Act: -0.0006

Data Index: 140336 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0896. Min Act: -0.0006

Data Index: 1292544 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0851. Min Act: -0.0006

Data Index: 913034 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0816. Min Act: -0.0006

Data Index: 986459 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0784. Min Act: -0.0006

Data Index: 386090 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0812. Min Act: -0.0006

Data Index: 497756 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0846. Min Act: -0.0006

Data Index: 213405 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0809. Min Act: -0.0006

Data Index: 338115 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0776. Min Act: -0.0006

Data Index: 84642 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0774. Min Act: -0.0006

Data Index: 976800 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0829. Min Act: -0.0006

Data Index: 744920 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0861. Min Act: -0.0006

Data Index: 526482 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0828. Min Act: -0.0006

Data Index: 1115090 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0821. Min Act: -0.0006

Data Index: 321191 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0791. Min Act: -0.0006

Data Index: 801087 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0758. Min Act: -0.0006

Data Index: 640341 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0821. Min Act: -0.0005

Data Index: 42963 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0850. Min Act: -0.0006

Data Index: 83858 (C4 (Web Text))

Max Activating Token Index: 653