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

Dataset: The Pile

Neuron 3120 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: 1.0516. Min Range: -1.0516

Max Act: 1.0516. Min Act: -0.0000

Data Index: 752010 (The Pile)

Max Activating Token Index: 781

Text #1

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.9972. Min Act: -0.0000

Data Index: 853579 (The Pile)

Max Activating Token Index: 939

Text #2

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1943469 (The Pile)

Max Activating Token Index: 272

Text #3

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1821786 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8632. Min Act: -0.0000

Data Index: 1349422 (The Pile)

Max Activating Token Index: 153

Text #5

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.9541. Min Act: -0.0000

Data Index: 678645 (The Pile)

Max Activating Token Index: 804

Text #6

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8074. Min Act: -0.0000

Data Index: 528358 (The Pile)

Max Activating Token Index: 660

Text #7

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.9821. Min Act: -0.0000

Data Index: 126297 (The Pile)

Max Activating Token Index: 927

Text #8

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.7867. Min Act: -0.0000

Data Index: 408440 (The Pile)

Max Activating Token Index: 639

Text #9

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8651. Min Act: -0.0000

Data Index: 414073 (The Pile)

Max Activating Token Index: 40

Text #10

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1791588 (The Pile)

Max Activating Token Index: 282

Text #11

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8055. Min Act: -0.0000

Data Index: 699897 (The Pile)

Max Activating Token Index: 752

Text #12

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8279. Min Act: -0.0000

Data Index: 62049 (The Pile)

Max Activating Token Index: 213

Text #13

Max Range: 1.0516. Min Range: -1.0516

Max Act: 1.0210. Min Act: -0.0000

Data Index: 1438990 (The Pile)

Max Activating Token Index: 221

Text #14

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8192. Min Act: -0.0000

Data Index: 1551798 (The Pile)

Max Activating Token Index: 546

Text #15

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1767940 (The Pile)

Max Activating Token Index: 825

Text #16

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8139. Min Act: -0.0000

Data Index: 19199 (The Pile)

Max Activating Token Index: 277

Text #17

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8424. Min Act: -0.0000

Data Index: 729001 (The Pile)

Max Activating Token Index: 959

Text #18

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8553. Min Act: -0.0000

Data Index: 465527 (The Pile)

Max Activating Token Index: 238

Text #19

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8898. Min Act: -0.0000

Data Index: 152378 (The Pile)

Max Activating Token Index: 117