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

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

Neuron 1343 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.7014. Min Act: -0.0000

Data Index: 209647 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.6340. Min Act: -0.0000

Data Index: 1492280 (Python Code)

Max Activating Token Index: 162

Text #2

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.6606. Min Act: -0.0000

Data Index: 351321 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1315033 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.5630. Min Act: -0.0000

Data Index: 1185358 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.5821. Min Act: -0.0001

Data Index: 253254 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1157033 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.6038. Min Act: -0.0000

Data Index: 660724 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.5184. Min Act: -0.0000

Data Index: 923291 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.5319. Min Act: -0.0001

Data Index: 90475 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1248599 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.5205. Min Act: -0.0000

Data Index: 176056 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1359840 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.5411. Min Act: -0.0000

Data Index: 402226 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.5191. Min Act: -0.0001

Data Index: 942097 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1337473 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.5045. Min Act: -0.0000

Data Index: 1278328 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.4903. Min Act: -0.0000

Data Index: 836589 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1309015 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.4720. Min Act: -0.0001

Data Index: 371976 (C4 (Web Text))

Max Activating Token Index: 491