Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1833 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.3155. Min Act: -0.0000

Data Index: 1228217 (The Pile)

Max Activating Token Index: 143

Text #1

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.3136. Min Act: -0.0000

Data Index: 24959 (The Pile)

Max Activating Token Index: 247

Text #2

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1825076 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2724. Min Act: -0.0000

Data Index: 1893896 (The Pile)

Max Activating Token Index: 503

Text #4

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1624660 (The Pile)

Max Activating Token Index: 100

Text #5

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2465. Min Act: -0.0000

Data Index: 1606671 (The Pile)

Max Activating Token Index: 197

Text #6

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2675. Min Act: -0.0000

Data Index: 294700 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2548. Min Act: -0.0000

Data Index: 507907 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2442. Min Act: -0.0000

Data Index: 472221 (The Pile)

Max Activating Token Index: 685

Text #9

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1141713 (The Pile)

Max Activating Token Index: 754

Text #10

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2449. Min Act: -0.0000

Data Index: 778814 (The Pile)

Max Activating Token Index: 913

Text #11

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2419. Min Act: -0.0000

Data Index: 445821 (The Pile)

Max Activating Token Index: 178

Text #12

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1571492 (The Pile)

Max Activating Token Index: 244

Text #13

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2418. Min Act: -0.0000

Data Index: 1369576 (The Pile)

Max Activating Token Index: 166

Text #14

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2414. Min Act: -0.0000

Data Index: 3496 (The Pile)

Max Activating Token Index: 703

Text #15

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1405185 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2381. Min Act: -0.0000

Data Index: 671873 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2457. Min Act: -0.0000

Data Index: 725229 (The Pile)

Max Activating Token Index: 972

Text #18

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2502. Min Act: -0.0000

Data Index: 1608284 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2343. Min Act: -0.0000

Data Index: 498957 (The Pile)

Max Activating Token Index: 224