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

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

Neuron 4049 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.3441. Min Act: -0.0000

Data Index: 1352961 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.3495. Min Act: -0.0001

Data Index: 760658 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.3166. Min Act: -0.0000

Data Index: 689470 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2963. Min Act: -0.0001

Data Index: 1357253 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1033151 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2983. Min Act: -0.0001

Data Index: 245832 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2896. Min Act: -0.0001

Data Index: 1196984 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2815. Min Act: -0.0001

Data Index: 793189 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2874. Min Act: -0.0000

Data Index: 737377 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2781. Min Act: -0.0001

Data Index: 839382 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2666. Min Act: -0.0001

Data Index: 143620 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2725. Min Act: -0.0000

Data Index: 240428 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2712. Min Act: -0.0000

Data Index: 99894 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2697. Min Act: -0.0000

Data Index: 64984 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2685. Min Act: -0.0000

Data Index: 620583 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2654. Min Act: -0.0000

Data Index: 480100 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2744. Min Act: -0.0000

Data Index: 357204 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2644. Min Act: -0.0000

Data Index: 894444 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2529. Min Act: -0.0000

Data Index: 705510 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.3495. Min Range: -0.3495

Max Act: 0.2611. Min Act: -0.0001

Data Index: 1122155 (C4 (Web Text))

Max Activating Token Index: 64