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

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

Neuron 225 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: 3.3066. Min Range: -3.3066

Max Act: 3.3066. Min Act: -0.0000

Data Index: 767006 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.9537. Min Act: -0.0000

Data Index: 469891 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.9845. Min Act: -0.0000

Data Index: 556011 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 3.3066. Min Range: -3.3066

Max Act: 3.1402. Min Act: -0.0000

Data Index: 540233 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.6017. Min Act: -0.0001

Data Index: 947683 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.5919. Min Act: -0.0000

Data Index: 1035898 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.3490. Min Act: -0.0000

Data Index: 807067 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.4326. Min Act: -0.0000

Data Index: 170679 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 3.3066. Min Range: -3.3066

Max Act: 1.9965. Min Act: -0.0000

Data Index: 140385 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.2525. Min Act: -0.0000

Data Index: 291830 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.2110. Min Act: -0.0000

Data Index: 412879 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.2804. Min Act: -0.0000

Data Index: 73494 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.3471. Min Act: -0.0000

Data Index: 395317 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.2053. Min Act: -0.0000

Data Index: 173224 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.1724. Min Act: -0.0000

Data Index: 788418 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.3945. Min Act: -0.0000

Data Index: 605834 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.4252. Min Act: -0.0000

Data Index: 656960 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.1603. Min Act: -0.0000

Data Index: 1177549 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.0469. Min Act: -0.0000

Data Index: 532052 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 3.3066. Min Range: -3.3066

Max Act: 2.0439. Min Act: -0.0000

Data Index: 690628 (C4 (Web Text))

Max Activating Token Index: 198