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

Dataset: The Pile

Neuron 3085 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: 0.2737. Min Range: -0.2737

Max Act: 0.2708. Min Act: -0.0000

Data Index: 653395 (The Pile)

Max Activating Token Index: 399

Text #1

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1199772 (The Pile)

Max Activating Token Index: 488

Text #2

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1364270 (The Pile)

Max Activating Token Index: 257

Text #3

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2495. Min Act: -0.0000

Data Index: 799736 (The Pile)

Max Activating Token Index: 572

Text #4

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1794088 (The Pile)

Max Activating Token Index: 967

Text #5

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2547. Min Act: -0.0000

Data Index: 6972 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2373. Min Act: -0.0000

Data Index: 858863 (The Pile)

Max Activating Token Index: 111

Text #7

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2373. Min Act: -0.0000

Data Index: 959609 (The Pile)

Max Activating Token Index: 111

Text #8

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2434. Min Act: -0.0000

Data Index: 355309 (The Pile)

Max Activating Token Index: 321

Text #9

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2252. Min Act: -0.0000

Data Index: 96498 (The Pile)

Max Activating Token Index: 861

Text #10

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2351. Min Act: -0.0000

Data Index: 573690 (The Pile)

Max Activating Token Index: 876

Text #11

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1835919 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1953354 (The Pile)

Max Activating Token Index: 700

Text #13

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2434. Min Act: -0.0000

Data Index: 725117 (The Pile)

Max Activating Token Index: 55

Text #14

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2348. Min Act: -0.0000

Data Index: 11844 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2203. Min Act: -0.0000

Data Index: 182915 (The Pile)

Max Activating Token Index: 162

Text #16

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2333. Min Act: -0.0000

Data Index: 629356 (The Pile)

Max Activating Token Index: 411

Text #17

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1967151 (The Pile)

Max Activating Token Index: 946

Text #18

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1409905 (The Pile)

Max Activating Token Index: 777

Text #19

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2460. Min Act: -0.0000

Data Index: 1001057 (The Pile)

Max Activating Token Index: 996