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

Dataset: The Pile

Neuron 3876 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: 0.9972. Min Range: -0.9972

Max Act: 0.9972. Min Act: -0.0000

Data Index: 348687 (The Pile)

Max Activating Token Index: 5

Text #1

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.8166. Min Act: -0.0000

Data Index: 1897291 (The Pile)

Max Activating Token Index: 537

Text #2

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.7704. Min Act: -0.0000

Data Index: 111475 (The Pile)

Max Activating Token Index: 581

Text #3

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.7778. Min Act: -0.0000

Data Index: 153049 (The Pile)

Max Activating Token Index: 513

Text #4

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.7232. Min Act: -0.0000

Data Index: 257983 (The Pile)

Max Activating Token Index: 369

Text #5

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.6985. Min Act: -0.0000

Data Index: 468614 (The Pile)

Max Activating Token Index: 323

Text #6

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.6199. Min Act: -0.0000

Data Index: 239844 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.7002. Min Act: -0.0000

Data Index: 562089 (The Pile)

Max Activating Token Index: 106

Text #8

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.6586. Min Act: -0.0000

Data Index: 132923 (The Pile)

Max Activating Token Index: 786

Text #9

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1517475 (The Pile)

Max Activating Token Index: 80

Text #10

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1518319 (The Pile)

Max Activating Token Index: 85

Text #11

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1751058 (The Pile)

Max Activating Token Index: 963

Text #12

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.6672. Min Act: -0.0000

Data Index: 954774 (The Pile)

Max Activating Token Index: 438

Text #13

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.6840. Min Act: -0.0000

Data Index: 1970234 (The Pile)

Max Activating Token Index: 212

Text #14

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1596198 (The Pile)

Max Activating Token Index: 321

Text #15

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.6350. Min Act: -0.0000

Data Index: 1797619 (The Pile)

Max Activating Token Index: 594

Text #16

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1959036 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.6262. Min Act: -0.0000

Data Index: 189568 (The Pile)

Max Activating Token Index: 264

Text #18

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1604883 (The Pile)

Max Activating Token Index: 465

Text #19

Max Range: 0.9972. Min Range: -0.9972

Max Act: 0.6055. Min Act: -0.0000

Data Index: 906705 (The Pile)

Max Activating Token Index: 162