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

Dataset: The Pile

Neuron 3410 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: 3.5001. Min Range: -3.5001

Max Act: 3.2254. Min Act: -0.0000

Data Index: 520681 (The Pile)

Max Activating Token Index: 134

Text #1

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.2079. Min Act: -0.0000

Data Index: 1036939 (The Pile)

Max Activating Token Index: 194

Text #2

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.2055. Min Act: -0.0000

Data Index: 840272 (The Pile)

Max Activating Token Index: 169

Text #3

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3212. Min Act: -0.0000

Data Index: 230559 (The Pile)

Max Activating Token Index: 304

Text #4

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.2965. Min Act: -0.0000

Data Index: 1243875 (The Pile)

Max Activating Token Index: 864

Text #5

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.2509. Min Act: -0.0000

Data Index: 662418 (The Pile)

Max Activating Token Index: 31

Text #6

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.2016. Min Act: -0.0000

Data Index: 1220809 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.5001. Min Act: -0.0000

Data Index: 939848 (The Pile)

Max Activating Token Index: 628

Text #8

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.1723. Min Act: -0.0000

Data Index: 798130 (The Pile)

Max Activating Token Index: 353

Text #9

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.0203. Min Act: -0.0000

Data Index: 816528 (The Pile)

Max Activating Token Index: 490

Text #10

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.1566. Min Act: -0.0000

Data Index: 976103 (The Pile)

Max Activating Token Index: 200

Text #11

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.0292. Min Act: -0.0001

Data Index: 303801 (The Pile)

Max Activating Token Index: 595

Text #12

Max Range: 3.5001. Min Range: -3.5001

Max Act: 2.8782. Min Act: -0.0000

Data Index: 418831 (The Pile)

Max Activating Token Index: 953

Text #13

Max Range: 3.5001. Min Range: -3.5001

Max Act: 2.9744. Min Act: -0.0000

Data Index: 1442091 (The Pile)

Max Activating Token Index: 610

Text #14

Max Range: 3.5001. Min Range: -3.5001

Max Act: 2.6874. Min Act: -0.0000

Data Index: 699949 (The Pile)

Max Activating Token Index: 132

Text #15

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.0879. Min Act: -0.0000

Data Index: 1887638 (The Pile)

Max Activating Token Index: 92

Text #16

Max Range: 3.5001. Min Range: -3.5001

Max Act: 2.9288. Min Act: -0.0001

Data Index: 1316100 (The Pile)

Max Activating Token Index: 523

Text #17

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.0745. Min Act: -0.0000

Data Index: 892542 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.0563. Min Act: -0.0000

Data Index: 1436148 (The Pile)

Max Activating Token Index: 9

Text #19

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.1794. Min Act: -0.0000

Data Index: 1353608 (The Pile)

Max Activating Token Index: 99