Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 545 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0766. Min Act: -0.0003

Data Index: 666403 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0702. Min Act: -0.0003

Data Index: 223999 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0811. Min Act: -0.0003

Data Index: 1181431 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0742. Min Act: -0.0003

Data Index: 794346 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0700. Min Act: -0.0003

Data Index: 851425 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0777. Min Act: -0.0003

Data Index: 500598 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0746. Min Act: -0.0003

Data Index: 474131 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0795. Min Act: -0.0003

Data Index: 403928 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0787. Min Act: -0.0003

Data Index: 443941 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0791. Min Act: -0.0003

Data Index: 146273 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0706. Min Act: -0.0003

Data Index: 1296593 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0704. Min Act: -0.0003

Data Index: 648300 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0658. Min Act: -0.0003

Data Index: 979472 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1132746 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0745. Min Act: -0.0003

Data Index: 480741 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0688. Min Act: -0.0003

Data Index: 251755 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0616. Min Act: -0.0003

Data Index: 46539 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0677. Min Act: -0.0003

Data Index: 748406 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0627. Min Act: -0.0003

Data Index: 1255310 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1348384 (C4 (Web Text))

Max Activating Token Index: 232