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

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

Neuron 2012 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.9404. Min Act: -0.0001

Data Index: 417576 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.9081. Min Act: -0.0001

Data Index: 1136623 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.9195. Min Act: -0.0001

Data Index: 469801 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.9006. Min Act: -0.0001

Data Index: 1192112 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.7495. Min Act: -0.0001

Data Index: 953794 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.9274. Min Act: -0.0001

Data Index: 728588 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.8848. Min Act: -0.0001

Data Index: 864957 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.7611. Min Act: -0.0001

Data Index: 1146290 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.7495. Min Act: -0.0000

Data Index: 504254 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.7102. Min Act: -0.0001

Data Index: 263024 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.7965. Min Act: -0.0001

Data Index: 1257153 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.6035. Min Act: -0.0001

Data Index: 44323 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.6001. Min Act: -0.0001

Data Index: 842587 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.6882. Min Act: -0.0001

Data Index: 764065 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.7528. Min Act: -0.0001

Data Index: 195673 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.4892. Min Act: -0.0000

Data Index: 597897 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.5742. Min Act: -0.0001

Data Index: 808865 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.6612. Min Act: -0.0001

Data Index: 100195 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.7503. Min Act: -0.0001

Data Index: 117523 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.6449. Min Act: -0.0001

Data Index: 880503 (C4 (Web Text))

Max Activating Token Index: 297