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

Dataset: The Pile

Neuron 4152 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: 0.8524. Min Range: -0.8524

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1467759 (The Pile)

Max Activating Token Index: 586

Text #1

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.6441. Min Act: -0.0000

Data Index: 873527 (The Pile)

Max Activating Token Index: 696

Text #2

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.7268. Min Act: -0.0000

Data Index: 572949 (The Pile)

Max Activating Token Index: 475

Text #3

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1974645 (The Pile)

Max Activating Token Index: 853

Text #4

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1300656 (The Pile)

Max Activating Token Index: 181

Text #5

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1003023 (The Pile)

Max Activating Token Index: 473

Text #6

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1828994 (The Pile)

Max Activating Token Index: 296

Text #7

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1419562 (The Pile)

Max Activating Token Index: 554

Text #8

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.6462. Min Act: -0.0000

Data Index: 542349 (The Pile)

Max Activating Token Index: 562

Text #9

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.6721. Min Act: -0.0000

Data Index: 29819 (The Pile)

Max Activating Token Index: 222

Text #10

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.6291. Min Act: -0.0000

Data Index: 775621 (The Pile)

Max Activating Token Index: 586

Text #11

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.6269. Min Act: -0.0000

Data Index: 718601 (The Pile)

Max Activating Token Index: 846

Text #12

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.6139. Min Act: -0.0000

Data Index: 1024465 (The Pile)

Max Activating Token Index: 583

Text #13

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.6429. Min Act: -0.0000

Data Index: 567622 (The Pile)

Max Activating Token Index: 997

Text #14

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.5755. Min Act: -0.0000

Data Index: 876344 (The Pile)

Max Activating Token Index: 890

Text #15

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.5963. Min Act: -0.0000

Data Index: 998835 (The Pile)

Max Activating Token Index: 933

Text #16

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.6279. Min Act: -0.0000

Data Index: 1037175 (The Pile)

Max Activating Token Index: 776

Text #17

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.6104. Min Act: -0.0000

Data Index: 914902 (The Pile)

Max Activating Token Index: 912

Text #18

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1571958 (The Pile)

Max Activating Token Index: 804

Text #19

Max Range: 0.8524. Min Range: -0.8524

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1502060 (The Pile)

Max Activating Token Index: 295