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

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

Neuron 5553 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.1701. Min Act: -0.0002

Data Index: 677721 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.1209. Min Act: -0.0002

Data Index: 1517836 (Python Code)

Max Activating Token Index: 601

Text #2

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.1199. Min Act: -0.0002

Data Index: 467698 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.1101. Min Act: -0.0002

Data Index: 911142 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.1094. Min Act: -0.0002

Data Index: 1436306 (Python Code)

Max Activating Token Index: 192

Text #5

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.1087. Min Act: -0.0002

Data Index: 1652249 (Python Code)

Max Activating Token Index: 248

Text #6

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.1035. Min Act: -0.0002

Data Index: 1550453 (Python Code)

Max Activating Token Index: 835

Text #7

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.1029. Min Act: -0.0002

Data Index: 1499340 (Python Code)

Max Activating Token Index: 536

Text #8

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.1006. Min Act: -0.0002

Data Index: 552460 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.0997. Min Act: -0.0002

Data Index: 1487542 (Python Code)

Max Activating Token Index: 200

Text #10

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.0963. Min Act: -0.0002

Data Index: 245562 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1651265 (Python Code)

Max Activating Token Index: 414

Text #12

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1561230 (Python Code)

Max Activating Token Index: 850

Text #13

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.0928. Min Act: -0.0002

Data Index: 343844 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1486147 (Python Code)

Max Activating Token Index: 829

Text #15

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.0922. Min Act: -0.0002

Data Index: 1618583 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1297224 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.0921. Min Act: -0.0002

Data Index: 1621372 (Python Code)

Max Activating Token Index: 179

Text #18

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1207775 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.1701. Min Range: -0.1701

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1610357 (Python Code)

Max Activating Token Index: 91