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

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

Neuron 4271 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0001

Data Index: 824424 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0980. Min Act: -0.0001

Data Index: 506420 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1015. Min Act: -0.0001

Data Index: 855441 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0968. Min Act: -0.0001

Data Index: 98927 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1026. Min Act: -0.0001

Data Index: 447405 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1039443 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1008. Min Act: -0.0001

Data Index: 516847 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0950. Min Act: -0.0001

Data Index: 860213 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0917. Min Act: -0.0001

Data Index: 378409 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0879. Min Act: -0.0001

Data Index: 526718 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1214830 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0849. Min Act: -0.0001

Data Index: 1234077 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1037206 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0829. Min Act: -0.0001

Data Index: 66714 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0780. Min Act: -0.0002

Data Index: 465974 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1264569 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0862. Min Act: -0.0001

Data Index: 234625 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0868. Min Act: -0.0001

Data Index: 467453 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0948. Min Act: -0.0001

Data Index: 584045 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0883. Min Act: -0.0001

Data Index: 230745 (C4 (Web Text))

Max Activating Token Index: 977