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

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

Neuron 3895 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.8419. Min Act: -0.0000

Data Index: 535995 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.7972. Min Act: -0.0000

Data Index: 513794 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.7743. Min Act: -0.0000

Data Index: 544864 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.7455. Min Act: -0.0000

Data Index: 202629 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1327828 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.7310. Min Act: -0.0000

Data Index: 520880 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.7006. Min Act: -0.0000

Data Index: 186949 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6698. Min Act: -0.0000

Data Index: 889106 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6638. Min Act: -0.0000

Data Index: 243381 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6226. Min Act: -0.0000

Data Index: 816807 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6129. Min Act: -0.0000

Data Index: 1031124 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6446. Min Act: -0.0001

Data Index: 322992 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.5937. Min Act: -0.0000

Data Index: 362908 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1137510 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.5944. Min Act: -0.0000

Data Index: 554325 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6096. Min Act: -0.0000

Data Index: 872517 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6017. Min Act: -0.0000

Data Index: 622117 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1209465 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.6106. Min Act: -0.0000

Data Index: 783106 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.8419. Min Range: -0.8419

Max Act: 0.5907. Min Act: -0.0001

Data Index: 128267 (C4 (Web Text))

Max Activating Token Index: 297