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

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

Neuron 571 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.8032. Min Act: -0.0000

Data Index: 765935 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.7875. Min Act: -0.0000

Data Index: 315294 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.7049. Min Act: -0.0000

Data Index: 160528 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6494. Min Act: -0.0000

Data Index: 659216 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6864. Min Act: -0.0000

Data Index: 723011 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6548. Min Act: -0.0000

Data Index: 121275 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1131622 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5829. Min Act: -0.0000

Data Index: 250320 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5801. Min Act: -0.0000

Data Index: 300075 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6413. Min Act: -0.0001

Data Index: 1274156 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6134. Min Act: -0.0001

Data Index: 698250 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6141. Min Act: -0.0000

Data Index: 243704 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5726. Min Act: -0.0000

Data Index: 849206 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6310. Min Act: -0.0000

Data Index: 904210 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5922. Min Act: -0.0000

Data Index: 434206 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5893. Min Act: -0.0000

Data Index: 332313 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5548. Min Act: -0.0000

Data Index: 781801 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5686. Min Act: -0.0001

Data Index: 540766 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5629. Min Act: -0.0000

Data Index: 673423 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5622. Min Act: -0.0000

Data Index: 388020 (C4 (Web Text))

Max Activating Token Index: 776