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

Dataset: The Pile

Neuron 3876 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.9922. Min Act: -0.0000

Data Index: 1499886 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1928590 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1793628 (The Pile)

Max Activating Token Index: 928

Text #3

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1989246 (The Pile)

Max Activating Token Index: 227

Text #4

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1341102 (The Pile)

Max Activating Token Index: 103

Text #5

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8225. Min Act: -0.0000

Data Index: 25449 (The Pile)

Max Activating Token Index: 10

Text #6

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8409. Min Act: -0.0000

Data Index: 286681 (The Pile)

Max Activating Token Index: 834

Text #7

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1892056 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7921. Min Act: -0.0000

Data Index: 347776 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8176. Min Act: -0.0000

Data Index: 767896 (The Pile)

Max Activating Token Index: 597

Text #10

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7608. Min Act: -0.0000

Data Index: 256008 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1822570 (The Pile)

Max Activating Token Index: 252

Text #12

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1589823 (The Pile)

Max Activating Token Index: 946

Text #13

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7788. Min Act: -0.0000

Data Index: 741129 (The Pile)

Max Activating Token Index: 186

Text #14

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1454091 (The Pile)

Max Activating Token Index: 729

Text #15

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1647752 (The Pile)

Max Activating Token Index: 284

Text #16

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7557. Min Act: -0.0000

Data Index: 703662 (The Pile)

Max Activating Token Index: 102

Text #17

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7538. Min Act: -0.0000

Data Index: 7398 (The Pile)

Max Activating Token Index: 272

Text #18

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7627. Min Act: -0.0000

Data Index: 435860 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7166. Min Act: -0.0000

Data Index: 1984210 (The Pile)

Max Activating Token Index: 419