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

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

Neuron 1830 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.5014. Min Act: -0.0000

Data Index: 1092289 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.3339. Min Act: -0.0000

Data Index: 390755 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.3268. Min Act: -0.0000

Data Index: 794378 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.1488. Min Act: -0.0000

Data Index: 1110113 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 4.5014. Min Range: -4.5014

Max Act: 3.9531. Min Act: -0.0000

Data Index: 263061 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 4.5014. Min Range: -4.5014

Max Act: 3.9381. Min Act: -0.0000

Data Index: 377102 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.0396. Min Act: -0.0000

Data Index: 998225 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 4.5014. Min Range: -4.5014

Max Act: 3.7704. Min Act: -0.0000

Data Index: 201603 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.1037. Min Act: -0.0000

Data Index: 752356 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 4.5014. Min Range: -4.5014

Max Act: 3.8877. Min Act: -0.0000

Data Index: 257778 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 4.5014. Min Range: -4.5014

Max Act: 3.7391. Min Act: -0.0000

Data Index: 272547 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.0123. Min Act: -0.0000

Data Index: 694728 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 4.5014. Min Range: -4.5014

Max Act: 3.6974. Min Act: -0.0000

Data Index: 758606 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 4.5014. Min Range: -4.5014

Max Act: 3.8308. Min Act: -0.0000

Data Index: 882530 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 4.5014. Min Range: -4.5014

Max Act: 3.7918. Min Act: -0.0000

Data Index: 1330574 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 4.5014. Min Range: -4.5014

Max Act: 3.9287. Min Act: -0.0000

Data Index: 114413 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 4.5014. Min Range: -4.5014

Max Act: 3.9007. Min Act: -0.0000

Data Index: 620559 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 4.5014. Min Range: -4.5014

Max Act: 3.5664. Min Act: -0.0000

Data Index: 778139 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 4.5014. Min Range: -4.5014

Max Act: 3.7103. Min Act: -0.0000

Data Index: 807336 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 4.5014. Min Range: -4.5014

Max Act: 3.8457. Min Act: -0.0000

Data Index: 671806 (C4 (Web Text))

Max Activating Token Index: 900