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

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

Neuron 6029 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.4538. Min Act: -0.0000

Data Index: 725832 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.4703. Min Act: -0.0000

Data Index: 730610 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1239838 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.4110. Min Act: -0.0000

Data Index: 717051 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1199040 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3943. Min Act: -0.0000

Data Index: 47753 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3780. Min Act: -0.0000

Data Index: 294957 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3732. Min Act: -0.0000

Data Index: 439871 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3455. Min Act: -0.0000

Data Index: 452414 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3506. Min Act: -0.0000

Data Index: 80912 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3595. Min Act: -0.0000

Data Index: 897490 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1069016 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1089571 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3351. Min Act: -0.0000

Data Index: 90819 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3306. Min Act: -0.0000

Data Index: 928318 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3013. Min Act: -0.0000

Data Index: 613050 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3098. Min Act: -0.0000

Data Index: 1067441 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1135048 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1106556 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.4703. Min Range: -0.4703

Max Act: 0.2683. Min Act: -0.0000

Data Index: 408614 (C4 (Web Text))

Max Activating Token Index: 286