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

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

Neuron 5146 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1327294 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.8899. Min Act: 0.0000

Data Index: 791809 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.8902. Min Act: -0.0000

Data Index: 652426 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.8899. Min Act: 0.0000

Data Index: 1542180 (Python Code)

Max Activating Token Index: 613

Text #4

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1277131 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.7482. Min Act: 0.0000

Data Index: 1508192 (Python Code)

Max Activating Token Index: 499

Text #6

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.7976. Min Act: -0.0000

Data Index: 1640466 (Python Code)

Max Activating Token Index: 378

Text #7

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.7911. Min Act: -0.0000

Data Index: 363387 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.7704. Min Act: -0.0000

Data Index: 641613 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.7694. Min Act: -0.0000

Data Index: 1316058 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1622089 (Python Code)

Max Activating Token Index: 509

Text #11

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.7549. Min Act: -0.0000

Data Index: 555336 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.7472. Min Act: 0.0000

Data Index: 1038226 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.7269. Min Act: -0.0000

Data Index: 905977 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1304332 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1223954 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.7018. Min Act: -0.0000

Data Index: 593432 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.6927. Min Act: -0.0000

Data Index: 305842 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1478047 (Python Code)

Max Activating Token Index: 267

Text #19

Max Range: 0.9758. Min Range: -0.9758

Max Act: 0.6662. Min Act: -0.0000

Data Index: 102285 (C4 (Web Text))

Max Activating Token Index: 634