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

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

Neuron 2752 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.6080. Min Act: -0.0000

Data Index: 210961 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.5867. Min Act: -0.0000

Data Index: 439099 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.5549. Min Act: -0.0000

Data Index: 627458 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4956. Min Act: -0.0000

Data Index: 82920 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1104326 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4462. Min Act: -0.0000

Data Index: 800161 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4090. Min Act: -0.0000

Data Index: 212837 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3966. Min Act: -0.0000

Data Index: 184085 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1112005 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4355. Min Act: -0.0000

Data Index: 298819 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3778. Min Act: -0.0000

Data Index: 481904 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3718. Min Act: -0.0000

Data Index: 473225 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3705. Min Act: -0.0000

Data Index: 603672 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3832. Min Act: -0.0000

Data Index: 742955 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3476. Min Act: -0.0000

Data Index: 1221977 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3699. Min Act: -0.0000

Data Index: 610021 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3571. Min Act: -0.0000

Data Index: 85533 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3569. Min Act: -0.0000

Data Index: 16526 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3675. Min Act: -0.0000

Data Index: 849858 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3514. Min Act: -0.0000

Data Index: 256002 (C4 (Web Text))

Max Activating Token Index: 703