Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 160 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1625. Min Range: -1.1625

Max Act: 1.1625. Min Act: -0.0001

Data Index: 733090 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.1625. Min Range: -1.1625

Max Act: 1.0417. Min Act: -0.0001

Data Index: 759911 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 1.1625. Min Range: -1.1625

Max Act: 1.0092. Min Act: -0.0001

Data Index: 82539 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.8270. Min Act: -0.0001

Data Index: 952332 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.8499. Min Act: -0.0001

Data Index: 393974 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.8292. Min Act: -0.0001

Data Index: 532190 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.8668. Min Act: -0.0001

Data Index: 162467 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.7458. Min Act: -0.0001

Data Index: 1171684 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.7563. Min Act: -0.0001

Data Index: 751121 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.6323. Min Act: -0.0001

Data Index: 1122759 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.9226. Min Act: -0.0001

Data Index: 1320358 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.6921. Min Act: -0.0001

Data Index: 1072329 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.7476. Min Act: -0.0001

Data Index: 773703 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.6446. Min Act: -0.0001

Data Index: 341361 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.6793. Min Act: -0.0001

Data Index: 924124 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.6885. Min Act: -0.0001

Data Index: 1125808 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.7108. Min Act: -0.0001

Data Index: 213630 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.6527. Min Act: -0.0001

Data Index: 1209925 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.7292. Min Act: -0.0001

Data Index: 1082646 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.7076. Min Act: -0.0001

Data Index: 167223 (C4 (Web Text))

Max Activating Token Index: 1003