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

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

Neuron 3451 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.1002. Min Act: -0.0001

Data Index: 132316 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0973. Min Act: -0.0001

Data Index: 422877 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.1043. Min Act: -0.0001

Data Index: 713684 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0984. Min Act: -0.0001

Data Index: 762295 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0985. Min Act: -0.0001

Data Index: 135569 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1025550 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0946. Min Act: -0.0001

Data Index: 304000 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1018833 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0776. Min Act: -0.0002

Data Index: 617034 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1127813 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0954. Min Act: -0.0001

Data Index: 745116 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1113394 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1324078 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0911. Min Act: -0.0001

Data Index: 297555 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0962. Min Act: -0.0002

Data Index: 232242 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0894. Min Act: -0.0001

Data Index: 935453 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0905. Min Act: -0.0002

Data Index: 458213 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1189044 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0821. Min Act: -0.0002

Data Index: 221933 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0876. Min Act: -0.0001

Data Index: 740394 (C4 (Web Text))

Max Activating Token Index: 877