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

Dataset: The Pile

Neuron 952 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1539917 (The Pile)

Max Activating Token Index: 771

Text #1

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.7004. Min Act: -0.0000

Data Index: 578236 (The Pile)

Max Activating Token Index: 458

Text #2

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1708301 (The Pile)

Max Activating Token Index: 59

Text #3

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1049547 (The Pile)

Max Activating Token Index: 411

Text #4

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6798. Min Act: -0.0000

Data Index: 125291 (The Pile)

Max Activating Token Index: 449

Text #5

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.7022. Min Act: -0.0000

Data Index: 1563269 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.5942. Min Act: -0.0000

Data Index: 68952 (The Pile)

Max Activating Token Index: 751

Text #7

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6195. Min Act: -0.0000

Data Index: 620289 (The Pile)

Max Activating Token Index: 961

Text #8

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1743029 (The Pile)

Max Activating Token Index: 682

Text #9

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6490. Min Act: -0.0000

Data Index: 758790 (The Pile)

Max Activating Token Index: 282

Text #10

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1344281 (The Pile)

Max Activating Token Index: 294

Text #11

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6341. Min Act: -0.0000

Data Index: 948283 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1825719 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6324. Min Act: -0.0000

Data Index: 767638 (The Pile)

Max Activating Token Index: 303

Text #14

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.5838. Min Act: -0.0000

Data Index: 602396 (The Pile)

Max Activating Token Index: 946

Text #15

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1530852 (The Pile)

Max Activating Token Index: 278

Text #16

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6170. Min Act: -0.0000

Data Index: 990985 (The Pile)

Max Activating Token Index: 190

Text #17

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6192. Min Act: -0.0000

Data Index: 525008 (The Pile)

Max Activating Token Index: 399

Text #18

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6012. Min Act: -0.0000

Data Index: 713562 (The Pile)

Max Activating Token Index: 477

Text #19

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1566426 (The Pile)

Max Activating Token Index: 348