Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3990 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2558. Min Act: -0.0001

Data Index: 1104146 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2425. Min Act: -0.0001

Data Index: 190324 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1813. Min Act: -0.0001

Data Index: 675309 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1918. Min Act: -0.0001

Data Index: 592911 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2182. Min Act: -0.0001

Data Index: 689458 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2058. Min Act: -0.0001

Data Index: 952607 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1783. Min Act: -0.0001

Data Index: 451135 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1936. Min Act: -0.0001

Data Index: 708367 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1957. Min Act: -0.0001

Data Index: 14228 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1855. Min Act: -0.0001

Data Index: 162350 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1743. Min Act: -0.0001

Data Index: 456086 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1768. Min Act: -0.0001

Data Index: 147765 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1795. Min Act: -0.0001

Data Index: 942383 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1723. Min Act: -0.0001

Data Index: 55601 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1918. Min Act: -0.0001

Data Index: 1259402 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1836. Min Act: -0.0001

Data Index: 1125540 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1951. Min Act: -0.0001

Data Index: 1112206 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1881. Min Act: -0.0001

Data Index: 72577 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1111606 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1793. Min Act: -0.0001

Data Index: 222200 (C4 (Web Text))

Max Activating Token Index: 276