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

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

Neuron 520 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.7662. Min Act: -0.0000

Data Index: 933637 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.8691. Min Act: -0.0000

Data Index: 611526 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.5590. Min Act: -0.0000

Data Index: 990043 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.2480. Min Act: -0.0000

Data Index: 316628 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.1847. Min Act: -0.0000

Data Index: 898121 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.3214. Min Act: -0.0000

Data Index: 847029 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.2601. Min Act: -0.0000

Data Index: 755051 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.2374. Min Act: -0.0000

Data Index: 402020 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.2098. Min Act: -0.0000

Data Index: 189160 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.2799. Min Act: -0.0000

Data Index: 1211522 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.1862. Min Act: -0.0000

Data Index: 473090 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.2101. Min Act: -0.0000

Data Index: 871567 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.1394. Min Act: -0.0000

Data Index: 2938 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.1598. Min Act: -0.0000

Data Index: 554724 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.1440. Min Act: -0.0000

Data Index: 409252 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.1311. Min Act: -0.0000

Data Index: 1081397 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.0680. Min Act: -0.0000

Data Index: 335635 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.0833. Min Act: -0.0000

Data Index: 261278 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.0575. Min Act: -0.0000

Data Index: 220512 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.0441. Min Act: -0.0000

Data Index: 1314614 (C4 (Web Text))

Max Activating Token Index: 931