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

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

Neuron 5119 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: 1.5909. Min Range: -1.5909

Max Act: 1.5707. Min Act: -0.0001

Data Index: 126559 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.5909. Min Act: -0.0001

Data Index: 1046026 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.5721. Min Act: -0.0000

Data Index: 656250 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3810. Min Act: -0.0001

Data Index: 178107 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.4005. Min Act: -0.0001

Data Index: 1093245 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3594. Min Act: -0.0001

Data Index: 307610 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.2691. Min Act: -0.0001

Data Index: 1322508 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3087. Min Act: -0.0000

Data Index: 971310 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3096. Min Act: -0.0000

Data Index: 308108 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.2974. Min Act: -0.0001

Data Index: 359423 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.2612. Min Act: -0.0001

Data Index: 197771 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.2961. Min Act: -0.0000

Data Index: 602124 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.2541. Min Act: -0.0001

Data Index: 959457 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.0973. Min Act: -0.0000

Data Index: 148302 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.0960. Min Act: -0.0001

Data Index: 496187 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.1812. Min Act: -0.0001

Data Index: 993733 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.2018. Min Act: -0.0000

Data Index: 178705 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.1962. Min Act: -0.0001

Data Index: 138840 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.1385. Min Act: -0.0000

Data Index: 645761 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.1120. Min Act: -0.0001

Data Index: 893463 (C4 (Web Text))

Max Activating Token Index: 11