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

Dataset: The Pile

Neuron 1478 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: 1.8724. Min Range: -1.8724

Max Act: 1.8724. Min Act: -0.0000

Data Index: 104746 (The Pile)

Max Activating Token Index: 534

Text #1

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.7245. Min Act: -0.0000

Data Index: 644113 (The Pile)

Max Activating Token Index: 725

Text #2

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.5241. Min Act: -0.0000

Data Index: 1000422 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.5572. Min Act: -0.0000

Data Index: 1811382 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.5002. Min Act: -0.0000

Data Index: 808477 (The Pile)

Max Activating Token Index: 283

Text #5

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.4047. Min Act: -0.0000

Data Index: 1358050 (The Pile)

Max Activating Token Index: 808

Text #6

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.4252. Min Act: -0.0000

Data Index: 1284760 (The Pile)

Max Activating Token Index: 783

Text #7

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.2314. Min Act: -0.0000

Data Index: 1465853 (The Pile)

Max Activating Token Index: 836

Text #8

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.3060. Min Act: -0.0000

Data Index: 1176239 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.1250. Min Act: -0.0000

Data Index: 1367374 (The Pile)

Max Activating Token Index: 652

Text #10

Max Range: 1.8724. Min Range: -1.8724

Max Act: 0.9752. Min Act: -0.0000

Data Index: 12782 (The Pile)

Max Activating Token Index: 965

Text #11

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.1471. Min Act: -0.0000

Data Index: 331523 (The Pile)

Max Activating Token Index: 242

Text #12

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1675658 (The Pile)

Max Activating Token Index: 693

Text #13

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.1637. Min Act: -0.0000

Data Index: 1729901 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.1528. Min Act: -0.0000

Data Index: 1156687 (The Pile)

Max Activating Token Index: 797

Text #15

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.1135. Min Act: -0.0000

Data Index: 221526 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.0407. Min Act: -0.0000

Data Index: 224035 (The Pile)

Max Activating Token Index: 618

Text #17

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.0674. Min Act: -0.0000

Data Index: 559057 (The Pile)

Max Activating Token Index: 499

Text #18

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.0381. Min Act: -0.0000

Data Index: 1807341 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 1.8724. Min Range: -1.8724

Max Act: 1.0322. Min Act: -0.0000

Data Index: 1577292 (The Pile)

Max Activating Token Index: 705