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

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

Neuron 3009 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1078779 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0922. Min Act: -0.0002

Data Index: 564146 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0886. Min Act: -0.0002

Data Index: 685557 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0847. Min Act: -0.0002

Data Index: 598289 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1396595 (Python Code)

Max Activating Token Index: 883

Text #5

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0809. Min Act: -0.0002

Data Index: 945306 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0785. Min Act: -0.0002

Data Index: 860824 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0773. Min Act: -0.0002

Data Index: 162417 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0776. Min Act: -0.0002

Data Index: 939587 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0759. Min Act: -0.0002

Data Index: 443642 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0778. Min Act: -0.0002

Data Index: 895172 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0768. Min Act: -0.0002

Data Index: 800006 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0748. Min Act: -0.0002

Data Index: 607675 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0739. Min Act: -0.0002

Data Index: 671395 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0749. Min Act: -0.0002

Data Index: 366159 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1461471 (Python Code)

Max Activating Token Index: 518

Text #16

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1341677 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0742. Min Act: -0.0002

Data Index: 153661 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0733. Min Act: -0.0002

Data Index: 357979 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0730. Min Act: -0.0002

Data Index: 439572 (C4 (Web Text))

Max Activating Token Index: 93