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

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

Neuron 5326 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.9030. Min Act: -0.0001

Data Index: 622572 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.9309. Min Act: -0.0001

Data Index: 61273 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.9398. Min Act: -0.0001

Data Index: 204267 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.9619. Min Act: -0.0001

Data Index: 8536 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.8233. Min Act: -0.0001

Data Index: 79889 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.8664. Min Act: -0.0001

Data Index: 404380 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.7529. Min Act: -0.0001

Data Index: 330125 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.5572. Min Act: -0.0001

Data Index: 743363 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.7333. Min Act: -0.0001

Data Index: 259340 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.5564. Min Act: -0.0001

Data Index: 1325417 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.8214. Min Act: -0.0001

Data Index: 617231 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.7079. Min Act: -0.0001

Data Index: 9838 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.6886. Min Act: -0.0001

Data Index: 562579 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.6239. Min Act: -0.0001

Data Index: 960503 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.7601. Min Act: -0.0001

Data Index: 448250 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.6483. Min Act: -0.0001

Data Index: 768784 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.4567. Min Act: -0.0001

Data Index: 102271 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.6552. Min Act: -0.0001

Data Index: 101467 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.6997. Min Act: -0.0001

Data Index: 523910 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 1.9619. Min Range: -1.9619

Max Act: 1.5084. Min Act: -0.0001

Data Index: 198008 (C4 (Web Text))

Max Activating Token Index: 378