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

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

Neuron 105 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.7386. Min Act: -0.0000

Data Index: 32626 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.6741. Min Act: -0.0000

Data Index: 122325 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.6119. Min Act: -0.0000

Data Index: 1002766 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.6601. Min Act: -0.0000

Data Index: 166687 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1181280 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5939. Min Act: -0.0000

Data Index: 63080 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5998. Min Act: -0.0000

Data Index: 410951 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5753. Min Act: -0.0000

Data Index: 867558 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1286302 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5507. Min Act: -0.0000

Data Index: 426108 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5102. Min Act: -0.0000

Data Index: 166636 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5483. Min Act: -0.0000

Data Index: 662813 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1280095 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5004. Min Act: -0.0000

Data Index: 300514 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5090. Min Act: -0.0000

Data Index: 764472 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5040. Min Act: -0.0000

Data Index: 810577 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5212. Min Act: -0.0000

Data Index: 51380 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5127. Min Act: -0.0000

Data Index: 152480 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.4933. Min Act: -0.0000

Data Index: 320192 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.4786. Min Act: -0.0000

Data Index: 325199 (C4 (Web Text))

Max Activating Token Index: 157