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

Dataset: The Pile

Neuron 1014 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1366. Min Range: -1.1366

Max Act: 1.1366. Min Act: -0.0000

Data Index: 782698 (The Pile)

Max Activating Token Index: 832

Text #1

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1951646 (The Pile)

Max Activating Token Index: 748

Text #2

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.9317. Min Act: -0.0000

Data Index: 1939266 (The Pile)

Max Activating Token Index: 716

Text #3

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1191861 (The Pile)

Max Activating Token Index: 775

Text #4

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1895519 (The Pile)

Max Activating Token Index: 656

Text #5

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1821175 (The Pile)

Max Activating Token Index: 386

Text #6

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1693760 (The Pile)

Max Activating Token Index: 819

Text #7

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8684. Min Act: -0.0000

Data Index: 666822 (The Pile)

Max Activating Token Index: 540

Text #8

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.9149. Min Act: -0.0000

Data Index: 1690354 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8939. Min Act: -0.0000

Data Index: 292709 (The Pile)

Max Activating Token Index: 873

Text #10

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8513. Min Act: -0.0000

Data Index: 842709 (The Pile)

Max Activating Token Index: 996

Text #11

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8289. Min Act: -0.0000

Data Index: 478934 (The Pile)

Max Activating Token Index: 604

Text #12

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8743. Min Act: -0.0000

Data Index: 1145276 (The Pile)

Max Activating Token Index: 977

Text #13

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1151147 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.7641. Min Act: -0.0000

Data Index: 60169 (The Pile)

Max Activating Token Index: 753

Text #15

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1311689 (The Pile)

Max Activating Token Index: 313

Text #16

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8569. Min Act: -0.0000

Data Index: 276957 (The Pile)

Max Activating Token Index: 536

Text #17

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.7686. Min Act: -0.0000

Data Index: 756165 (The Pile)

Max Activating Token Index: 246

Text #18

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.7481. Min Act: -0.0000

Data Index: 247726 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.7492. Min Act: -0.0000

Data Index: 943074 (The Pile)

Max Activating Token Index: 391