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

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

Neuron 704 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.7254. Min Act: -0.0000

Data Index: 957277 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.7470. Min Act: -0.0000

Data Index: 369331 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1103238 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1162522 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.7068. Min Act: -0.0000

Data Index: 415528 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.6846. Min Act: -0.0000

Data Index: 896373 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.7288. Min Act: -0.0000

Data Index: 138445 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.6975. Min Act: -0.0000

Data Index: 763258 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.6917. Min Act: -0.0000

Data Index: 66570 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.6865. Min Act: -0.0000

Data Index: 181891 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.6683. Min Act: -0.0000

Data Index: 443668 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.6848. Min Act: -0.0000

Data Index: 833749 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.6699. Min Act: -0.0000

Data Index: 435866 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.6699. Min Act: -0.0000

Data Index: 866801 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1240163 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.6657. Min Act: -0.0000

Data Index: 102959 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.6579. Min Act: -0.0000

Data Index: 746063 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.6518. Min Act: -0.0000

Data Index: 927360 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1315444 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.7470. Min Range: -0.7470

Max Act: 0.6911. Min Act: -0.0000

Data Index: 854545 (C4 (Web Text))

Max Activating Token Index: 988