Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 802 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2444. Min Act: -0.0005

Data Index: 25889 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2286. Min Act: -0.0005

Data Index: 58759 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2359. Min Act: -0.0005

Data Index: 1342116 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2121. Min Act: -0.0005

Data Index: 563506 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2102. Min Act: -0.0005

Data Index: 701269 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2078. Min Act: -0.0005

Data Index: 660016 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2023. Min Act: -0.0005

Data Index: 1101270 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2052. Min Act: -0.0005

Data Index: 1297386 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1884. Min Act: -0.0005

Data Index: 88142 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1965. Min Act: -0.0005

Data Index: 1323867 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2075. Min Act: -0.0005

Data Index: 104605 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1866. Min Act: -0.0005

Data Index: 856694 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1814. Min Act: -0.0005

Data Index: 742828 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1753. Min Act: -0.0005

Data Index: 956763 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1946. Min Act: -0.0005

Data Index: 904032 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1864. Min Act: -0.0005

Data Index: 88974 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1611. Min Act: -0.0005

Data Index: 503238 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1845. Min Act: -0.0005

Data Index: 698664 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1710. Min Act: -0.0005

Data Index: 1132132 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1765. Min Act: -0.0005

Data Index: 1106452 (C4 (Web Text))

Max Activating Token Index: 580