Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 124 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.1044. Min Act: -0.0003

Data Index: 836583 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0967. Min Act: -0.0003

Data Index: 691065 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0839. Min Act: -0.0003

Data Index: 1310472 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0880. Min Act: -0.0003

Data Index: 1023547 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0860. Min Act: -0.0004

Data Index: 700155 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0839. Min Act: -0.0003

Data Index: 216878 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0829. Min Act: -0.0004

Data Index: 934284 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0836. Min Act: -0.0003

Data Index: 1149020 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0804. Min Act: -0.0003

Data Index: 950410 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0797. Min Act: -0.0004

Data Index: 771088 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0788. Min Act: -0.0004

Data Index: 694330 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0766. Min Act: -0.0003

Data Index: 69705 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0744. Min Act: -0.0003

Data Index: 269880 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0739. Min Act: -0.0003

Data Index: 1196996 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0676. Min Act: -0.0004

Data Index: 526196 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1577509 (Python Code)

Max Activating Token Index: 842

Text #16

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0708. Min Act: -0.0003

Data Index: 44245 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0698. Min Act: -0.0003

Data Index: 667123 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0734. Min Act: -0.0003

Data Index: 1380676 (Python Code)

Max Activating Token Index: 972

Text #19

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0694. Min Act: -0.0003

Data Index: 1228717 (C4 (Web Text))

Max Activating Token Index: 1005