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

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

Neuron 1155 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: 0.9785. Min Range: -0.9785

Max Act: 0.9785. Min Act: -0.0000

Data Index: 1055775 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8721. Min Act: -0.0000

Data Index: 362877 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1396706 (Python Code)

Max Activating Token Index: 704

Text #3

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.7841. Min Act: -0.0000

Data Index: 841541 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8084. Min Act: -0.0000

Data Index: 454729 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1065253 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6951. Min Act: -0.0000

Data Index: 963213 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6691. Min Act: -0.0000

Data Index: 182462 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1322956 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1147926 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6822. Min Act: -0.0000

Data Index: 7263 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6406. Min Act: -0.0000

Data Index: 481205 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6180. Min Act: -0.0000

Data Index: 110319 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.5940. Min Act: -0.0000

Data Index: 485825 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.5548. Min Act: -0.0000

Data Index: 253956 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.7144. Min Act: -0.0000

Data Index: 250656 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.5742. Min Act: -0.0000

Data Index: 658877 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.5804. Min Act: -0.0000

Data Index: 772445 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1001827 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.5062. Min Act: -0.0000

Data Index: 650076 (C4 (Web Text))

Max Activating Token Index: 159