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

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

Neuron 1846 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: 0.8038. Min Range: -0.8038

Max Act: 0.8038. Min Act: -0.0000

Data Index: 504780 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6590. Min Act: -0.0000

Data Index: 196367 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.5865. Min Act: -0.0000

Data Index: 328901 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.5948. Min Act: -0.0000

Data Index: 621019 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.5815. Min Act: -0.0000

Data Index: 514537 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.5592. Min Act: -0.0000

Data Index: 174700 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1012050 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.5492. Min Act: 0.0000

Data Index: 923708 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.4937. Min Act: -0.0000

Data Index: 283590 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.5051. Min Act: -0.0000

Data Index: 319198 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1226919 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.4841. Min Act: -0.0000

Data Index: 465768 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.4542. Min Act: -0.0000

Data Index: 738662 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1046863 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.4906. Min Act: -0.0000

Data Index: 401249 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.4887. Min Act: -0.0000

Data Index: 580287 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1108680 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.4813. Min Act: -0.0000

Data Index: 164175 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.4766. Min Act: -0.0000

Data Index: 491498 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.4729. Min Act: -0.0000

Data Index: 862381 (C4 (Web Text))

Max Activating Token Index: 93