Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1753 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.4244. Min Act: -0.0003

Data Index: 1155474 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0493. Min Act: -0.0003

Data Index: 93041 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0353. Min Act: -0.0003

Data Index: 937727 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0020. Min Act: -0.0003

Data Index: 1044916 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0872. Min Act: -0.0003

Data Index: 226006 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.1009. Min Act: -0.0003

Data Index: 708102 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.9709. Min Act: -0.0003

Data Index: 459235 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.9629. Min Act: -0.0003

Data Index: 308159 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0129. Min Act: -0.0003

Data Index: 424008 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0121. Min Act: -0.0003

Data Index: 497079 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0057. Min Act: -0.0003

Data Index: 78901 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.7677. Min Act: -0.0003

Data Index: 402018 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.8960. Min Act: -0.0003

Data Index: 798427 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0804. Min Act: -0.0003

Data Index: 294452 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.8180. Min Act: -0.0003

Data Index: 879182 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.9730. Min Act: -0.0003

Data Index: 320757 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.9403. Min Act: -0.0003

Data Index: 394633 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.7800. Min Act: -0.0003

Data Index: 1036417 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.8645. Min Act: -0.0003

Data Index: 816142 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.8469. Min Act: -0.0003

Data Index: 918430 (C4 (Web Text))

Max Activating Token Index: 752