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

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

Neuron 5813 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.4782. Min Act: -0.0000

Data Index: 1185469 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.0142. Min Act: -0.0000

Data Index: 1270737 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.9333. Min Act: -0.0000

Data Index: 822821 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.9664. Min Act: -0.0000

Data Index: 628120 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.8920. Min Act: -0.0000

Data Index: 843706 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.8580. Min Act: 0.0000

Data Index: 205216 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.8497. Min Act: -0.0000

Data Index: 656451 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.8427. Min Act: -0.0000

Data Index: 147689 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.8433. Min Act: -0.0000

Data Index: 813530 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.8105. Min Act: 0.0000

Data Index: 174386 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.7964. Min Act: -0.0000

Data Index: 780616 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.7580. Min Act: -0.0000

Data Index: 420604 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.7802. Min Act: 0.0000

Data Index: 1314774 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.7546. Min Act: 0.0000

Data Index: 509603 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.7519. Min Act: -0.0000

Data Index: 341281 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.7052. Min Act: 0.0000

Data Index: 1346619 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.7472. Min Act: -0.0000

Data Index: 833660 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.8224. Min Act: -0.0000

Data Index: 868463 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.7088. Min Act: 0.0000

Data Index: 880745 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.7047. Min Act: -0.0000

Data Index: 863886 (C4 (Web Text))

Max Activating Token Index: 71