Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1918 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1440. Min Range: -1.1440

Max Act: 1.1440. Min Act: -0.0000

Data Index: 1122731 (The Pile)

Max Activating Token Index: 775

Text #1

Max Range: 1.1440. Min Range: -1.1440

Max Act: 1.1030. Min Act: -0.0000

Data Index: 611898 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 1.1440. Min Range: -1.1440

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1088551 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8982. Min Act: -0.0000

Data Index: 921606 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1437614 (The Pile)

Max Activating Token Index: 614

Text #5

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1615534 (The Pile)

Max Activating Token Index: 66

Text #6

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8430. Min Act: -0.0000

Data Index: 657370 (The Pile)

Max Activating Token Index: 504

Text #7

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1373418 (The Pile)

Max Activating Token Index: 280

Text #8

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8881. Min Act: -0.0000

Data Index: 539442 (The Pile)

Max Activating Token Index: 837

Text #9

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1039666 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1110197 (The Pile)

Max Activating Token Index: 213

Text #11

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1309149 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1187323 (The Pile)

Max Activating Token Index: 978

Text #13

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.7767. Min Act: -0.0000

Data Index: 1584014 (The Pile)

Max Activating Token Index: 60

Text #14

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8304. Min Act: -0.0000

Data Index: 917865 (The Pile)

Max Activating Token Index: 910

Text #15

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.7971. Min Act: -0.0000

Data Index: 32999 (The Pile)

Max Activating Token Index: 613

Text #16

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.7776. Min Act: -0.0000

Data Index: 883047 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8034. Min Act: -0.0000

Data Index: 347173 (The Pile)

Max Activating Token Index: 486

Text #18

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8254. Min Act: -0.0000

Data Index: 1975485 (The Pile)

Max Activating Token Index: 890

Text #19

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8197. Min Act: -0.0000

Data Index: 529708 (The Pile)

Max Activating Token Index: 70