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

Dataset: The Pile

Neuron 560 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: 1.0223. Min Range: -1.0223

Max Act: 1.0050. Min Act: -0.0000

Data Index: 642092 (The Pile)

Max Activating Token Index: 55

Text #1

Max Range: 1.0223. Min Range: -1.0223

Max Act: 1.0223. Min Act: -0.0000

Data Index: 691760 (The Pile)

Max Activating Token Index: 884

Text #2

Max Range: 1.0223. Min Range: -1.0223

Max Act: 1.0070. Min Act: -0.0000

Data Index: 1938263 (The Pile)

Max Activating Token Index: 870

Text #3

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.9364. Min Act: -0.0000

Data Index: 814927 (The Pile)

Max Activating Token Index: 874

Text #4

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1421590 (The Pile)

Max Activating Token Index: 290

Text #5

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1317671 (The Pile)

Max Activating Token Index: 11

Text #6

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1071643 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8481. Min Act: -0.0000

Data Index: 326750 (The Pile)

Max Activating Token Index: 523

Text #8

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7882. Min Act: -0.0000

Data Index: 527874 (The Pile)

Max Activating Token Index: 128

Text #9

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1200821 (The Pile)

Max Activating Token Index: 624

Text #10

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1031764 (The Pile)

Max Activating Token Index: 726

Text #11

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1061230 (The Pile)

Max Activating Token Index: 456

Text #12

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8748. Min Act: -0.0000

Data Index: 779625 (The Pile)

Max Activating Token Index: 750

Text #13

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1491652 (The Pile)

Max Activating Token Index: 960

Text #14

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1533886 (The Pile)

Max Activating Token Index: 898

Text #15

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1194547 (The Pile)

Max Activating Token Index: 421

Text #16

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7816. Min Act: -0.0000

Data Index: 1724739 (The Pile)

Max Activating Token Index: 455

Text #17

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7737. Min Act: -0.0000

Data Index: 1520714 (The Pile)

Max Activating Token Index: 650

Text #18

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7419. Min Act: -0.0000

Data Index: 353565 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1238770 (The Pile)

Max Activating Token Index: 911