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

Dataset: The Pile

Neuron 1926 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: 0.8884. Min Range: -0.8884

Max Act: 0.8504. Min Act: -0.0000

Data Index: 966281 (The Pile)

Max Activating Token Index: 928

Text #1

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.8442. Min Act: -0.0000

Data Index: 620455 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.8884. Min Act: 0.0000

Data Index: 1009181 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.8156. Min Act: 0.0000

Data Index: 1557033 (The Pile)

Max Activating Token Index: 838

Text #4

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.8262. Min Act: 0.0000

Data Index: 613865 (The Pile)

Max Activating Token Index: 215

Text #5

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1025323 (The Pile)

Max Activating Token Index: 108

Text #6

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1724651 (The Pile)

Max Activating Token Index: 769

Text #7

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.7638. Min Act: -0.0000

Data Index: 259013 (The Pile)

Max Activating Token Index: 498

Text #8

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1242977 (The Pile)

Max Activating Token Index: 953

Text #9

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.7606. Min Act: -0.0000

Data Index: 1999362 (The Pile)

Max Activating Token Index: 102

Text #10

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.7566. Min Act: -0.0000

Data Index: 489836 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.7412. Min Act: -0.0000

Data Index: 298433 (The Pile)

Max Activating Token Index: 836

Text #12

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.7574. Min Act: -0.0000

Data Index: 881539 (The Pile)

Max Activating Token Index: 605

Text #13

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.7571. Min Act: -0.0000

Data Index: 794506 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.7249. Min Act: 0.0000

Data Index: 1905693 (The Pile)

Max Activating Token Index: 768

Text #15

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1311839 (The Pile)

Max Activating Token Index: 817

Text #16

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.7409. Min Act: -0.0000

Data Index: 699843 (The Pile)

Max Activating Token Index: 924

Text #17

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1881713 (The Pile)

Max Activating Token Index: 699

Text #18

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.7123. Min Act: -0.0000

Data Index: 763490 (The Pile)

Max Activating Token Index: 603

Text #19

Max Range: 0.8884. Min Range: -0.8884

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1679203 (The Pile)

Max Activating Token Index: 461