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

Dataset: The Pile

Neuron 4646 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.3540. Min Act: -0.0000

Data Index: 1569845 (The Pile)

Max Activating Token Index: 689

Text #1

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1316105 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2823. Min Act: -0.0000

Data Index: 631645 (The Pile)

Max Activating Token Index: 182

Text #3

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1117669 (The Pile)

Max Activating Token Index: 59

Text #4

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2840. Min Act: -0.0000

Data Index: 653692 (The Pile)

Max Activating Token Index: 509

Text #5

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2704. Min Act: -0.0000

Data Index: 619855 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2547. Min Act: -0.0000

Data Index: 1702128 (The Pile)

Max Activating Token Index: 253

Text #7

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1685964 (The Pile)

Max Activating Token Index: 694

Text #8

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2547. Min Act: -0.0000

Data Index: 623623 (The Pile)

Max Activating Token Index: 562

Text #9

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.1916. Min Act: -0.0000

Data Index: 653204 (The Pile)

Max Activating Token Index: 843

Text #10

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2200. Min Act: -0.0000

Data Index: 351001 (The Pile)

Max Activating Token Index: 829

Text #11

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2579. Min Act: -0.0000

Data Index: 1159993 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2652. Min Act: -0.0000

Data Index: 266062 (The Pile)

Max Activating Token Index: 257

Text #13

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2290. Min Act: -0.0000

Data Index: 1935115 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2530. Min Act: -0.0000

Data Index: 700594 (The Pile)

Max Activating Token Index: 155

Text #15

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2352. Min Act: -0.0000

Data Index: 419119 (The Pile)

Max Activating Token Index: 79

Text #16

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1202590 (The Pile)

Max Activating Token Index: 372

Text #17

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2569. Min Act: -0.0000

Data Index: 1449735 (The Pile)

Max Activating Token Index: 578

Text #18

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2178. Min Act: -0.0000

Data Index: 95176 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 0.3540. Min Range: -0.3540

Max Act: 0.2394. Min Act: -0.0000

Data Index: 65943 (The Pile)

Max Activating Token Index: 626