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

Dataset: The Pile

Neuron 503 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: 1.7804. Min Range: -1.7804

Max Act: 1.7804. Min Act: -0.0000

Data Index: 464472 (The Pile)

Max Activating Token Index: 232

Text #1

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.7323. Min Act: -0.0000

Data Index: 1479664 (The Pile)

Max Activating Token Index: 499

Text #2

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.7084. Min Act: -0.0000

Data Index: 54281 (The Pile)

Max Activating Token Index: 111

Text #3

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.7025. Min Act: -0.0000

Data Index: 1257836 (The Pile)

Max Activating Token Index: 538

Text #4

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.6274. Min Act: -0.0000

Data Index: 1062946 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.5631. Min Act: -0.0000

Data Index: 1511958 (The Pile)

Max Activating Token Index: 534

Text #6

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.6229. Min Act: -0.0000

Data Index: 751360 (The Pile)

Max Activating Token Index: 235

Text #7

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.5710. Min Act: -0.0000

Data Index: 883124 (The Pile)

Max Activating Token Index: 990

Text #8

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.5976. Min Act: -0.0000

Data Index: 1612937 (The Pile)

Max Activating Token Index: 651

Text #9

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.5097. Min Act: -0.0000

Data Index: 1542884 (The Pile)

Max Activating Token Index: 8

Text #10

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4533. Min Act: -0.0000

Data Index: 1605933 (The Pile)

Max Activating Token Index: 736

Text #11

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.5373. Min Act: -0.0000

Data Index: 1738253 (The Pile)

Max Activating Token Index: 57

Text #12

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4903. Min Act: -0.0000

Data Index: 1939575 (The Pile)

Max Activating Token Index: 860

Text #13

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4843. Min Act: -0.0000

Data Index: 1049134 (The Pile)

Max Activating Token Index: 508

Text #14

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4861. Min Act: -0.0000

Data Index: 1559476 (The Pile)

Max Activating Token Index: 709

Text #15

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4816. Min Act: -0.0000

Data Index: 338797 (The Pile)

Max Activating Token Index: 497

Text #16

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4339. Min Act: -0.0000

Data Index: 505678 (The Pile)

Max Activating Token Index: 384

Text #17

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4435. Min Act: -0.0000

Data Index: 578417 (The Pile)

Max Activating Token Index: 894

Text #18

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.3040. Min Act: -0.0000

Data Index: 757875 (The Pile)

Max Activating Token Index: 952

Text #19

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4185. Min Act: -0.0000

Data Index: 1363093 (The Pile)

Max Activating Token Index: 834