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

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

Neuron 1739 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: 0.7824. Min Range: -0.7824

Max Act: 0.7824. Min Act: -0.0000

Data Index: 571250 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7721. Min Act: -0.0000

Data Index: 923184 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.7208. Min Act: -0.0000

Data Index: 686043 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6977. Min Act: -0.0000

Data Index: 855809 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6577. Min Act: -0.0000

Data Index: 370391 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6914. Min Act: -0.0000

Data Index: 762134 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6778. Min Act: -0.0000

Data Index: 630305 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1142344 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1021365 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1052910 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6726. Min Act: -0.0000

Data Index: 131304 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6877. Min Act: -0.0000

Data Index: 929640 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6244. Min Act: -0.0000

Data Index: 33677 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6429. Min Act: -0.0000

Data Index: 799532 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6061. Min Act: -0.0000

Data Index: 297988 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6325. Min Act: -0.0000

Data Index: 354854 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6712. Min Act: -0.0000

Data Index: 338072 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6461. Min Act: -0.0000

Data Index: 308706 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.6166. Min Act: -0.0000

Data Index: 279172 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.7824. Min Range: -0.7824

Max Act: 0.5611. Min Act: -0.0000

Data Index: 34756 (C4 (Web Text))

Max Activating Token Index: 274