Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2068 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.9914. Min Act: -0.0000

Data Index: 354364 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.8416. Min Act: -0.0000

Data Index: 1305634 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.4702. Min Act: -0.0000

Data Index: 807415 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.6018. Min Act: -0.0000

Data Index: 693404 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.5159. Min Act: -0.0000

Data Index: 988447 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.4862. Min Act: -0.0000

Data Index: 1213800 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.3305. Min Act: -0.0000

Data Index: 516069 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.4645. Min Act: -0.0000

Data Index: 628558 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.2782. Min Act: -0.0000

Data Index: 1300762 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.5729. Min Act: -0.0000

Data Index: 276709 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.2753. Min Act: -0.0000

Data Index: 1035329 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.8791. Min Act: -0.0000

Data Index: 414369 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.2275. Min Act: -0.0000

Data Index: 841548 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.2158. Min Act: -0.0000

Data Index: 276903 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.2675. Min Act: -0.0000

Data Index: 405454 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.2083. Min Act: -0.0000

Data Index: 342092 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.2042. Min Act: -0.0000

Data Index: 70341 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.2071. Min Act: -0.0000

Data Index: 715149 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.1957. Min Act: -0.0000

Data Index: 1114510 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.1905. Min Act: -0.0000

Data Index: 569059 (C4 (Web Text))

Max Activating Token Index: 125