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

Dataset: The Pile

Neuron 2007 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: 1.1268. Min Range: -1.1268

Max Act: 1.1268. Min Act: -0.0000

Data Index: 869386 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 1.1268. Min Range: -1.1268

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1574861 (The Pile)

Max Activating Token Index: 970

Text #2

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8948. Min Act: -0.0000

Data Index: 784454 (The Pile)

Max Activating Token Index: 837

Text #3

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.9472. Min Act: -0.0000

Data Index: 1303943 (The Pile)

Max Activating Token Index: 871

Text #4

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.9556. Min Act: -0.0000

Data Index: 234472 (The Pile)

Max Activating Token Index: 395

Text #5

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.9423. Min Act: -0.0000

Data Index: 680735 (The Pile)

Max Activating Token Index: 298

Text #6

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.9317. Min Act: -0.0000

Data Index: 722 (The Pile)

Max Activating Token Index: 667

Text #7

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8746. Min Act: -0.0000

Data Index: 1671568 (The Pile)

Max Activating Token Index: 727

Text #8

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1056540 (The Pile)

Max Activating Token Index: 778

Text #9

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.9352. Min Act: -0.0000

Data Index: 920217 (The Pile)

Max Activating Token Index: 914

Text #10

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1967607 (The Pile)

Max Activating Token Index: 963

Text #11

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1649072 (The Pile)

Max Activating Token Index: 453

Text #12

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1440083 (The Pile)

Max Activating Token Index: 914

Text #13

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8816. Min Act: -0.0000

Data Index: 1683383 (The Pile)

Max Activating Token Index: 754

Text #14

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1798131 (The Pile)

Max Activating Token Index: 988

Text #15

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1510275 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1946259 (The Pile)

Max Activating Token Index: 737

Text #17

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.9419. Min Act: -0.0000

Data Index: 1309674 (The Pile)

Max Activating Token Index: 1003

Text #18

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8252. Min Act: -0.0000

Data Index: 1358067 (The Pile)

Max Activating Token Index: 410

Text #19

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8170. Min Act: -0.0001

Data Index: 1699066 (The Pile)

Max Activating Token Index: 366