Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3863 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.8605. Min Act: -0.0000

Data Index: 209378 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7880. Min Act: -0.0000

Data Index: 404371 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7512. Min Act: -0.0000

Data Index: 72200 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.8077. Min Act: -0.0000

Data Index: 83936 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7633. Min Act: -0.0000

Data Index: 261391 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7616. Min Act: -0.0000

Data Index: 23003 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7384. Min Act: -0.0000

Data Index: 40661 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1170927 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1100927 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1309723 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7014. Min Act: -0.0000

Data Index: 572084 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.6812. Min Act: -0.0000

Data Index: 603460 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.6525. Min Act: -0.0000

Data Index: 600969 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7138. Min Act: -0.0000

Data Index: 770399 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.6881. Min Act: -0.0000

Data Index: 294340 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.6693. Min Act: -0.0000

Data Index: 756884 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.6228. Min Act: -0.0000

Data Index: 300597 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.6403. Min Act: -0.0000

Data Index: 407943 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.6383. Min Act: -0.0000

Data Index: 740531 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1267314 (C4 (Web Text))

Max Activating Token Index: 892