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

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

Neuron 2190 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7688. Min Act: -0.0001

Data Index: 1234210 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7648. Min Act: -0.0001

Data Index: 880846 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7385. Min Act: -0.0001

Data Index: 632881 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7371. Min Act: -0.0001

Data Index: 492360 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7383. Min Act: -0.0001

Data Index: 1084426 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7186. Min Act: -0.0001

Data Index: 1293792 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7073. Min Act: -0.0001

Data Index: 361607 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6562. Min Act: -0.0001

Data Index: 1119093 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6368. Min Act: -0.0001

Data Index: 1008749 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6699. Min Act: -0.0001

Data Index: 677409 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6775. Min Act: -0.0001

Data Index: 471186 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6685. Min Act: -0.0001

Data Index: 63897 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6662. Min Act: -0.0001

Data Index: 648933 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6506. Min Act: -0.0001

Data Index: 1177901 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5843. Min Act: -0.0001

Data Index: 1274905 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6223. Min Act: -0.0001

Data Index: 1344289 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6288. Min Act: -0.0001

Data Index: 706435 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5786. Min Act: -0.0001

Data Index: 257527 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6620. Min Act: -0.0001

Data Index: 877764 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6134. Min Act: -0.0001

Data Index: 426830 (C4 (Web Text))

Max Activating Token Index: 275