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

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

Neuron 5989 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1170336 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1602891 (Python Code)

Max Activating Token Index: 902

Text #2

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1304. Min Act: -0.0000

Data Index: 816462 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1524855 (Python Code)

Max Activating Token Index: 197

Text #4

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1590406 (Python Code)

Max Activating Token Index: 768

Text #5

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1100. Min Act: -0.0000

Data Index: 115123 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1050. Min Act: -0.0000

Data Index: 313955 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.0944. Min Act: -0.0000

Data Index: 1561450 (Python Code)

Max Activating Token Index: 971

Text #8

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1600918 (Python Code)

Max Activating Token Index: 784

Text #9

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1593249 (Python Code)

Max Activating Token Index: 998

Text #10

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1075. Min Act: -0.0000

Data Index: 259901 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1504503 (Python Code)

Max Activating Token Index: 861

Text #12

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.0968. Min Act: -0.0000

Data Index: 90753 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1378338 (Python Code)

Max Activating Token Index: 402

Text #14

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1505936 (Python Code)

Max Activating Token Index: 274

Text #15

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.0912. Min Act: -0.0000

Data Index: 1615453 (Python Code)

Max Activating Token Index: 646

Text #16

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.0872. Min Act: -0.0000

Data Index: 1364447 (Python Code)

Max Activating Token Index: 249

Text #17

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.0891. Min Act: -0.0000

Data Index: 284743 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1617689 (Python Code)

Max Activating Token Index: 429

Text #19

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.0898. Min Act: -0.0000

Data Index: 64491 (C4 (Web Text))

Max Activating Token Index: 1004