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

Dataset: The Pile

Neuron 4201 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: 3.0663. Min Range: -3.0663

Max Act: 2.9423. Min Act: -0.0000

Data Index: 1348050 (The Pile)

Max Activating Token Index: 141

Text #1

Max Range: 3.0663. Min Range: -3.0663

Max Act: 3.0663. Min Act: -0.0000

Data Index: 756149 (The Pile)

Max Activating Token Index: 304

Text #2

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.7017. Min Act: -0.0000

Data Index: 337813 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.4724. Min Act: -0.0000

Data Index: 758565 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.6800. Min Act: -0.0000

Data Index: 399032 (The Pile)

Max Activating Token Index: 875

Text #5

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.6424. Min Act: -0.0000

Data Index: 1207832 (The Pile)

Max Activating Token Index: 535

Text #6

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.5032. Min Act: -0.0000

Data Index: 849777 (The Pile)

Max Activating Token Index: 203

Text #7

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.1124. Min Act: -0.0000

Data Index: 1215573 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.3325. Min Act: -0.0000

Data Index: 193008 (The Pile)

Max Activating Token Index: 793

Text #9

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.2460. Min Act: -0.0000

Data Index: 1751273 (The Pile)

Max Activating Token Index: 795

Text #10

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.2654. Min Act: -0.0000

Data Index: 1821882 (The Pile)

Max Activating Token Index: 290

Text #11

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.5820. Min Act: -0.0000

Data Index: 1571097 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.3413. Min Act: -0.0000

Data Index: 1278965 (The Pile)

Max Activating Token Index: 742

Text #13

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.2847. Min Act: -0.0000

Data Index: 736315 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.1258. Min Act: -0.0000

Data Index: 771871 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.0707. Min Act: -0.0000

Data Index: 1865870 (The Pile)

Max Activating Token Index: 395

Text #16

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.1248. Min Act: -0.0000

Data Index: 619007 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.1238. Min Act: -0.0000

Data Index: 1958051 (The Pile)

Max Activating Token Index: 55

Text #18

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.0006. Min Act: -0.0000

Data Index: 348011 (The Pile)

Max Activating Token Index: 275

Text #19

Max Range: 3.0663. Min Range: -3.0663

Max Act: 1.9898. Min Act: -0.0000

Data Index: 58627 (The Pile)

Max Activating Token Index: 539