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

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

Neuron 3235 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1350661 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.1002. Min Act: -0.0001

Data Index: 138766 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0951. Min Act: -0.0001

Data Index: 395790 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1251306 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1005370 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0901. Min Act: -0.0001

Data Index: 812931 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0843. Min Act: -0.0001

Data Index: 902159 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0863. Min Act: -0.0001

Data Index: 364323 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0830. Min Act: -0.0001

Data Index: 879823 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0880. Min Act: -0.0001

Data Index: 353628 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0851. Min Act: -0.0001

Data Index: 1262604 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0841. Min Act: -0.0001

Data Index: 1321705 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0836. Min Act: -0.0001

Data Index: 262779 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0827. Min Act: -0.0001

Data Index: 97102 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1092312 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0800. Min Act: -0.0001

Data Index: 1095849 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1209286 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0792. Min Act: -0.0001

Data Index: 372679 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0763. Min Act: -0.0001

Data Index: 424367 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0761. Min Act: -0.0001

Data Index: 578961 (C4 (Web Text))

Max Activating Token Index: 438