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

Dataset: The Pile

Neuron 180 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: 1.4775. Min Range: -1.4775

Max Act: 1.4775. Min Act: -0.0000

Data Index: 524554 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.4533. Min Act: -0.0000

Data Index: 246751 (The Pile)

Max Activating Token Index: 938

Text #2

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.3116. Min Act: -0.0000

Data Index: 1511878 (The Pile)

Max Activating Token Index: 666

Text #3

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.3867. Min Act: -0.0000

Data Index: 1715369 (The Pile)

Max Activating Token Index: 280

Text #4

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.4272. Min Act: -0.0000

Data Index: 1673826 (The Pile)

Max Activating Token Index: 823

Text #5

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.2260. Min Act: -0.0000

Data Index: 694982 (The Pile)

Max Activating Token Index: 452

Text #6

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.1023. Min Act: -0.0000

Data Index: 1989469 (The Pile)

Max Activating Token Index: 896

Text #7

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.1846. Min Act: -0.0000

Data Index: 313337 (The Pile)

Max Activating Token Index: 871

Text #8

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.0338. Min Act: -0.0000

Data Index: 244484 (The Pile)

Max Activating Token Index: 458

Text #9

Max Range: 1.4775. Min Range: -1.4775

Max Act: 0.9957. Min Act: -0.0000

Data Index: 203827 (The Pile)

Max Activating Token Index: 674

Text #10

Max Range: 1.4775. Min Range: -1.4775

Max Act: 0.9959. Min Act: -0.0000

Data Index: 603573 (The Pile)

Max Activating Token Index: 209

Text #11

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.0525. Min Act: -0.0000

Data Index: 1949346 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 1.4775. Min Range: -1.4775

Max Act: 0.9737. Min Act: -0.0000

Data Index: 388187 (The Pile)

Max Activating Token Index: 508

Text #13

Max Range: 1.4775. Min Range: -1.4775

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1630975 (The Pile)

Max Activating Token Index: 928

Text #14

Max Range: 1.4775. Min Range: -1.4775

Max Act: 0.9787. Min Act: -0.0000

Data Index: 324293 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 1.4775. Min Range: -1.4775

Max Act: 1.0032. Min Act: -0.0000

Data Index: 1088573 (The Pile)

Max Activating Token Index: 618

Text #16

Max Range: 1.4775. Min Range: -1.4775

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1537401 (The Pile)

Max Activating Token Index: 189

Text #17

Max Range: 1.4775. Min Range: -1.4775

Max Act: 0.9860. Min Act: -0.0000

Data Index: 123868 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 1.4775. Min Range: -1.4775

Max Act: 0.8848. Min Act: -0.0000

Data Index: 85184 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 1.4775. Min Range: -1.4775

Max Act: 0.9374. Min Act: -0.0000

Data Index: 505568 (The Pile)

Max Activating Token Index: 93