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

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

Neuron 2772 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.6467. Min Range: -6.6467

Max Act: 6.6467. Min Act: -0.0000

Data Index: 784049 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 6.6467. Min Range: -6.6467

Max Act: 5.7764. Min Act: -0.0000

Data Index: 1052580 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 6.6467. Min Range: -6.6467

Max Act: 5.5030. Min Act: -0.0000

Data Index: 1217105 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 6.6467. Min Range: -6.6467

Max Act: 5.9427. Min Act: -0.0000

Data Index: 171877 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 6.6467. Min Range: -6.6467

Max Act: 5.6453. Min Act: -0.0000

Data Index: 31609 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 6.6467. Min Range: -6.6467

Max Act: 5.1326. Min Act: -0.0000

Data Index: 1018868 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 6.6467. Min Range: -6.6467

Max Act: 5.0596. Min Act: -0.0000

Data Index: 221513 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 6.6467. Min Range: -6.6467

Max Act: 5.9170. Min Act: -0.0000

Data Index: 1271995 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 6.6467. Min Range: -6.6467

Max Act: 4.9368. Min Act: -0.0000

Data Index: 751627 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 6.6467. Min Range: -6.6467

Max Act: 4.8577. Min Act: -0.0000

Data Index: 1036843 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 6.6467. Min Range: -6.6467

Max Act: 5.1217. Min Act: -0.0000

Data Index: 250842 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 6.6467. Min Range: -6.6467

Max Act: 5.2696. Min Act: -0.0000

Data Index: 440215 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 6.6467. Min Range: -6.6467

Max Act: 5.2717. Min Act: -0.0000

Data Index: 266838 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 6.6467. Min Range: -6.6467

Max Act: 4.7211. Min Act: -0.0000

Data Index: 613622 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 6.6467. Min Range: -6.6467

Max Act: 4.2898. Min Act: -0.0000

Data Index: 999945 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 6.6467. Min Range: -6.6467

Max Act: 4.8001. Min Act: -0.0000

Data Index: 1033056 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 6.6467. Min Range: -6.6467

Max Act: 4.6134. Min Act: -0.0000

Data Index: 623207 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 6.6467. Min Range: -6.6467

Max Act: 4.7201. Min Act: -0.0000

Data Index: 369269 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 6.6467. Min Range: -6.6467

Max Act: 4.4959. Min Act: -0.0000

Data Index: 907225 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 6.6467. Min Range: -6.6467

Max Act: 4.4882. Min Act: -0.0000

Data Index: 914367 (C4 (Web Text))

Max Activating Token Index: 522