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

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

Neuron 980 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: 1.4772. Min Range: -1.4772

Max Act: 1.4772. Min Act: -0.0000

Data Index: 958346 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.4245. Min Act: -0.0000

Data Index: 1301008 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.3954. Min Act: -0.0000

Data Index: 572712 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.3827. Min Act: -0.0000

Data Index: 1353111 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1165830 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.2068. Min Act: -0.0000

Data Index: 420868 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.3575. Min Act: -0.0000

Data Index: 342297 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.2691. Min Act: -0.0000

Data Index: 797508 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.3129. Min Act: -0.0000

Data Index: 992626 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.3029. Min Act: -0.0000

Data Index: 418510 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.1888. Min Act: -0.0000

Data Index: 775586 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.2434. Min Act: -0.0000

Data Index: 1064935 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.2334. Min Act: -0.0000

Data Index: 279267 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.2061. Min Act: -0.0000

Data Index: 814926 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.1747. Min Act: -0.0000

Data Index: 481059 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.2407. Min Act: -0.0000

Data Index: 16632 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.2753. Min Act: -0.0000

Data Index: 1652652 (Python Code)

Max Activating Token Index: 719

Text #17

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.2178. Min Act: -0.0000

Data Index: 814285 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.2825. Min Act: -0.0000

Data Index: 1042774 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 1.4772. Min Range: -1.4772

Max Act: 1.0978. Min Act: -0.0000

Data Index: 1081482 (C4 (Web Text))

Max Activating Token Index: 87