Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 881 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6981. Min Act: -0.0001

Data Index: 927027 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6108. Min Act: -0.0001

Data Index: 403637 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5720. Min Act: -0.0000

Data Index: 775855 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6057. Min Act: -0.0001

Data Index: 566946 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5756. Min Act: -0.0001

Data Index: 860791 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.4882. Min Act: -0.0001

Data Index: 555754 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5733. Min Act: -0.0001

Data Index: 173554 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5158. Min Act: -0.0001

Data Index: 194335 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.4988. Min Act: -0.0001

Data Index: 1076261 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.4935. Min Act: -0.0001

Data Index: 34372 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.4702. Min Act: -0.0001

Data Index: 1081784 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1048864 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.4653. Min Act: -0.0000

Data Index: 956806 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.4867. Min Act: -0.0001

Data Index: 909921 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.4653. Min Act: -0.0001

Data Index: 905224 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.4792. Min Act: -0.0000

Data Index: 117281 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.4741. Min Act: -0.0001

Data Index: 1283812 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.4471. Min Act: -0.0001

Data Index: 279504 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.4585. Min Act: -0.0000

Data Index: 824119 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.4761. Min Act: -0.0001

Data Index: 1259880 (C4 (Web Text))

Max Activating Token Index: 547