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

Dataset: The Pile

Neuron 4797 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: 0.4232. Min Range: -0.4232

Max Act: 0.4232. Min Act: -0.0000

Data Index: 35036 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1480502 (The Pile)

Max Activating Token Index: 472

Text #2

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.3068. Min Act: -0.0000

Data Index: 174546 (The Pile)

Max Activating Token Index: 98

Text #3

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2595. Min Act: -0.0000

Data Index: 50789 (The Pile)

Max Activating Token Index: 714

Text #4

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1200474 (The Pile)

Max Activating Token Index: 87

Text #5

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2635. Min Act: -0.0000

Data Index: 1247818 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2640. Min Act: -0.0000

Data Index: 1974888 (The Pile)

Max Activating Token Index: 435

Text #7

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2660. Min Act: -0.0000

Data Index: 951039 (The Pile)

Max Activating Token Index: 934

Text #8

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1264803 (The Pile)

Max Activating Token Index: 892

Text #9

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2619. Min Act: -0.0000

Data Index: 325023 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2435. Min Act: -0.0000

Data Index: 599323 (The Pile)

Max Activating Token Index: 625

Text #11

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2587. Min Act: -0.0000

Data Index: 799426 (The Pile)

Max Activating Token Index: 1000

Text #12

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2590. Min Act: -0.0000

Data Index: 475214 (The Pile)

Max Activating Token Index: 591

Text #13

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2126. Min Act: -0.0000

Data Index: 423958 (The Pile)

Max Activating Token Index: 961

Text #14

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2418. Min Act: -0.0000

Data Index: 587354 (The Pile)

Max Activating Token Index: 586

Text #15

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1196608 (The Pile)

Max Activating Token Index: 459

Text #16

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1830050 (The Pile)

Max Activating Token Index: 889

Text #17

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2298. Min Act: -0.0000

Data Index: 780821 (The Pile)

Max Activating Token Index: 586

Text #18

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1664373 (The Pile)

Max Activating Token Index: 848

Text #19

Max Range: 0.4232. Min Range: -0.4232

Max Act: 0.2381. Min Act: -0.0000

Data Index: 583002 (The Pile)

Max Activating Token Index: 138