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

Dataset: The Pile

Neuron 824 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: 0.6589. Min Range: -0.6589

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1147752 (The Pile)

Max Activating Token Index: 398

Text #1

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1580956 (The Pile)

Max Activating Token Index: 581

Text #2

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5238. Min Act: -0.0000

Data Index: 427131 (The Pile)

Max Activating Token Index: 179

Text #3

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1103776 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1288224 (The Pile)

Max Activating Token Index: 726

Text #5

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5082. Min Act: -0.0000

Data Index: 700625 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4434. Min Act: -0.0000

Data Index: 498312 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4721. Min Act: -0.0000

Data Index: 1050448 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4653. Min Act: -0.0000

Data Index: 542559 (The Pile)

Max Activating Token Index: 819

Text #9

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4449. Min Act: -0.0000

Data Index: 427719 (The Pile)

Max Activating Token Index: 444

Text #10

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1984656 (The Pile)

Max Activating Token Index: 1022

Text #11

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1383133 (The Pile)

Max Activating Token Index: 342

Text #12

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1802957 (The Pile)

Max Activating Token Index: 613

Text #13

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.3789. Min Act: -0.0000

Data Index: 790727 (The Pile)

Max Activating Token Index: 723

Text #14

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1937114 (The Pile)

Max Activating Token Index: 1012

Text #15

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1118276 (The Pile)

Max Activating Token Index: 829

Text #16

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4038. Min Act: -0.0000

Data Index: 13901 (The Pile)

Max Activating Token Index: 553

Text #17

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4014. Min Act: -0.0000

Data Index: 1297393 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.3905. Min Act: -0.0000

Data Index: 647576 (The Pile)

Max Activating Token Index: 769

Text #19

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.4327. Min Act: -0.0000

Data Index: 423257 (The Pile)

Max Activating Token Index: 963