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

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

Neuron 4645 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.7031. Min Act: -0.0000

Data Index: 897199 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.6441. Min Act: -0.0000

Data Index: 748232 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.6430. Min Act: -0.0000

Data Index: 1158361 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.5850. Min Act: -0.0000

Data Index: 201584 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.5466. Min Act: -0.0000

Data Index: 1080815 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.5174. Min Act: -0.0000

Data Index: 786123 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.4603. Min Act: -0.0000

Data Index: 1065546 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.4502. Min Act: -0.0000

Data Index: 766380 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.5228. Min Act: -0.0000

Data Index: 739567 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.4896. Min Act: -0.0000

Data Index: 1329972 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.3832. Min Act: -0.0000

Data Index: 449249 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.3761. Min Act: -0.0000

Data Index: 1176641 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.2719. Min Act: -0.0000

Data Index: 1227571 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.3529. Min Act: -0.0000

Data Index: 663738 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.2334. Min Act: -0.0000

Data Index: 90046 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.2956. Min Act: -0.0000

Data Index: 474046 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.2068. Min Act: -0.0000

Data Index: 103122 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.2866. Min Act: -0.0000

Data Index: 1331817 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.2414. Min Act: -0.0000

Data Index: 622950 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.2287. Min Act: -0.0000

Data Index: 800539 (C4 (Web Text))

Max Activating Token Index: 702