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

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

Neuron 3894 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.9268. Min Act: -0.0000

Data Index: 1311549 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.8312. Min Act: 0.0000

Data Index: 649565 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.7313. Min Act: -0.0000

Data Index: 960453 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6852. Min Act: -0.0000

Data Index: 417755 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6817. Min Act: -0.0000

Data Index: 561901 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1121784 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6515. Min Act: -0.0000

Data Index: 816026 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1347600 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1359476 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.5993. Min Act: -0.0000

Data Index: 19150 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1197665 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.5360. Min Act: -0.0000

Data Index: 65396 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.5799. Min Act: -0.0000

Data Index: 156278 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1018832 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.5334. Min Act: -0.0000

Data Index: 20613 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.5291. Min Act: -0.0000

Data Index: 923510 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.5597. Min Act: 0.0000

Data Index: 324733 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.5613. Min Act: 0.0000

Data Index: 1133715 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.5491. Min Act: -0.0000

Data Index: 453789 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.9268. Min Range: -0.9268

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1000820 (C4 (Web Text))

Max Activating Token Index: 859