Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 85 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.5997. Min Act: -0.0002

Data Index: 951286 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.5662. Min Act: -0.0002

Data Index: 721918 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.5223. Min Act: -0.0002

Data Index: 132646 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.5242. Min Act: -0.0002

Data Index: 1097900 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.5155. Min Act: -0.0002

Data Index: 820242 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.5310. Min Act: -0.0002

Data Index: 1181632 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.4888. Min Act: -0.0002

Data Index: 324458 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.4985. Min Act: -0.0002

Data Index: 1268309 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.4892. Min Act: -0.0002

Data Index: 778403 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.4936. Min Act: -0.0002

Data Index: 659545 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.4953. Min Act: -0.0002

Data Index: 62308 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.4874. Min Act: -0.0002

Data Index: 607858 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.5037. Min Act: -0.0002

Data Index: 318355 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.4794. Min Act: -0.0002

Data Index: 999222 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.4608. Min Act: -0.0002

Data Index: 1130789 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.4838. Min Act: -0.0003

Data Index: 894637 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.5139. Min Act: -0.0002

Data Index: 917572 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.4515. Min Act: -0.0002

Data Index: 1019387 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.4526. Min Act: -0.0002

Data Index: 268137 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.4800. Min Act: -0.0002

Data Index: 636613 (C4 (Web Text))

Max Activating Token Index: 568