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

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

Neuron 3018 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: 3.4801. Min Range: -3.4801

Max Act: 3.4801. Min Act: -0.0000

Data Index: 810636 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 3.4801. Min Range: -3.4801

Max Act: 2.3027. Min Act: -0.0000

Data Index: 1199965 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 3.4801. Min Range: -3.4801

Max Act: 2.4863. Min Act: -0.0000

Data Index: 642479 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 3.4801. Min Range: -3.4801

Max Act: 2.4632. Min Act: -0.0000

Data Index: 1148528 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 3.4801. Min Range: -3.4801

Max Act: 2.2610. Min Act: -0.0000

Data Index: 705337 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 3.4801. Min Range: -3.4801

Max Act: 2.1961. Min Act: -0.0000

Data Index: 1357789 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 3.4801. Min Range: -3.4801

Max Act: 2.1936. Min Act: -0.0000

Data Index: 965515 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 3.4801. Min Range: -3.4801

Max Act: 2.1862. Min Act: -0.0000

Data Index: 576626 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 3.4801. Min Range: -3.4801

Max Act: 2.1206. Min Act: -0.0000

Data Index: 961440 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 3.4801. Min Range: -3.4801

Max Act: 2.1402. Min Act: -0.0000

Data Index: 467034 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 3.4801. Min Range: -3.4801

Max Act: 2.1314. Min Act: -0.0000

Data Index: 485506 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 3.4801. Min Range: -3.4801

Max Act: 2.0100. Min Act: -0.0000

Data Index: 975960 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 3.4801. Min Range: -3.4801

Max Act: 1.7456. Min Act: -0.0000

Data Index: 755123 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 3.4801. Min Range: -3.4801

Max Act: 1.8977. Min Act: -0.0000

Data Index: 561024 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 3.4801. Min Range: -3.4801

Max Act: 1.8688. Min Act: -0.0000

Data Index: 417102 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 3.4801. Min Range: -3.4801

Max Act: 1.8365. Min Act: -0.0000

Data Index: 635360 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 3.4801. Min Range: -3.4801

Max Act: 1.8284. Min Act: -0.0000

Data Index: 58384 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 3.4801. Min Range: -3.4801

Max Act: 1.7927. Min Act: -0.0000

Data Index: 666437 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 3.4801. Min Range: -3.4801

Max Act: 1.8268. Min Act: -0.0000

Data Index: 304125 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 3.4801. Min Range: -3.4801

Max Act: 1.7811. Min Act: -0.0000

Data Index: 321053 (C4 (Web Text))

Max Activating Token Index: 724