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

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

Neuron 4154 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.7764. Min Act: -0.0000

Data Index: 460542 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.7081. Min Act: -0.0000

Data Index: 590336 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.7550. Min Act: -0.0000

Data Index: 531115 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.7117. Min Act: -0.0000

Data Index: 165981 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.7049. Min Act: -0.0000

Data Index: 945988 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1080187 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6401. Min Act: -0.0000

Data Index: 317254 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6859. Min Act: -0.0000

Data Index: 59175 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1101646 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6995. Min Act: -0.0000

Data Index: 529463 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6610. Min Act: -0.0000

Data Index: 865758 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6525. Min Act: -0.0000

Data Index: 979778 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1168984 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6992. Min Act: -0.0000

Data Index: 929367 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1272966 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6529. Min Act: -0.0000

Data Index: 387612 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5759. Min Act: -0.0000

Data Index: 824745 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5871. Min Act: -0.0000

Data Index: 648821 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.5804. Min Act: -0.0000

Data Index: 548995 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.7764. Min Range: -0.7764

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1343154 (C4 (Web Text))

Max Activating Token Index: 259