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

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

Neuron 3822 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1632404 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1357085 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.3508. Min Act: -0.0000

Data Index: 965168 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.3506. Min Act: -0.0000

Data Index: 376314 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.3255. Min Act: -0.0000

Data Index: 427220 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.3231. Min Act: 0.0001

Data Index: 1616307 (Python Code)

Max Activating Token Index: 60

Text #6

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1649001 (Python Code)

Max Activating Token Index: 435

Text #7

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.3095. Min Act: 0.0000

Data Index: 1477564 (Python Code)

Max Activating Token Index: 1011

Text #8

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.3016. Min Act: -0.0000

Data Index: 184009 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.2647. Min Act: -0.0000

Data Index: 385145 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1500679 (Python Code)

Max Activating Token Index: 536

Text #11

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.2920. Min Act: -0.0000

Data Index: 42425 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.2934. Min Act: -0.0000

Data Index: 837435 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.2923. Min Act: -0.0000

Data Index: 680822 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.3033. Min Act: -0.0000

Data Index: 410973 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.2804. Min Act: -0.0000

Data Index: 604642 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.2870. Min Act: -0.0000

Data Index: 413986 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.2753. Min Act: -0.0000

Data Index: 869612 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1155181 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.3819. Min Range: -0.3819

Max Act: 0.2817. Min Act: -0.0000

Data Index: 263626 (C4 (Web Text))

Max Activating Token Index: 630