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

Dataset: The Pile

Neuron 1679 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: 0.5766. Min Range: -0.5766

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1194056 (The Pile)

Max Activating Token Index: 195

Text #1

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.5229. Min Act: -0.0000

Data Index: 848837 (The Pile)

Max Activating Token Index: 584

Text #2

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1670537 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1869366 (The Pile)

Max Activating Token Index: 785

Text #4

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1869533 (The Pile)

Max Activating Token Index: 324

Text #5

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1301922 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4441. Min Act: -0.0000

Data Index: 671617 (The Pile)

Max Activating Token Index: 80

Text #7

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1408083 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1581458 (The Pile)

Max Activating Token Index: 549

Text #9

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1872615 (The Pile)

Max Activating Token Index: 972

Text #10

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1300972 (The Pile)

Max Activating Token Index: 751

Text #11

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4145. Min Act: -0.0000

Data Index: 818378 (The Pile)

Max Activating Token Index: 85

Text #12

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4137. Min Act: -0.0000

Data Index: 767047 (The Pile)

Max Activating Token Index: 54

Text #13

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.3980. Min Act: -0.0000

Data Index: 309354 (The Pile)

Max Activating Token Index: 912

Text #14

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4140. Min Act: -0.0000

Data Index: 1539440 (The Pile)

Max Activating Token Index: 715

Text #15

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4085. Min Act: -0.0000

Data Index: 562541 (The Pile)

Max Activating Token Index: 662

Text #16

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1803572 (The Pile)

Max Activating Token Index: 506

Text #17

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4174. Min Act: -0.0000

Data Index: 854560 (The Pile)

Max Activating Token Index: 656

Text #18

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4296. Min Act: -0.0000

Data Index: 664686 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1479802 (The Pile)

Max Activating Token Index: 1009