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

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

Neuron 539 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1947. Min Act: -0.0000

Data Index: 731759 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1646. Min Act: -0.0001

Data Index: 606145 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1158. Min Act: -0.0000

Data Index: 1430182 (Python Code)

Max Activating Token Index: 457

Text #3

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1260483 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1058. Min Act: -0.0000

Data Index: 383745 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1335747 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0936. Min Act: -0.0000

Data Index: 185393 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1423652 (Python Code)

Max Activating Token Index: 694

Text #8

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0911. Min Act: -0.0000

Data Index: 386764 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0872. Min Act: -0.0000

Data Index: 1490980 (Python Code)

Max Activating Token Index: 474

Text #10

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0964. Min Act: -0.0000

Data Index: 128642 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0949. Min Act: -0.0000

Data Index: 599013 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1532060 (Python Code)

Max Activating Token Index: 910

Text #13

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1228795 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1470864 (Python Code)

Max Activating Token Index: 890

Text #15

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0898. Min Act: -0.0000

Data Index: 1238337 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0840. Min Act: -0.0000

Data Index: 1450315 (Python Code)

Max Activating Token Index: 390

Text #17

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1590700 (Python Code)

Max Activating Token Index: 670

Text #18

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0821. Min Act: -0.0000

Data Index: 1437944 (Python Code)

Max Activating Token Index: 342

Text #19

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0810. Min Act: -0.0000

Data Index: 737600 (C4 (Web Text))

Max Activating Token Index: 350