Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2658 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.3815. Min Act: -0.0000

Data Index: 1980706 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.0690. Min Act: -0.0000

Data Index: 326204 (The Pile)

Max Activating Token Index: 951

Text #2

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1176316 (The Pile)

Max Activating Token Index: 442

Text #3

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.0056. Min Act: -0.0000

Data Index: 22684 (The Pile)

Max Activating Token Index: 28

Text #4

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.0311. Min Act: -0.0000

Data Index: 146585 (The Pile)

Max Activating Token Index: 190

Text #5

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9705. Min Act: -0.0000

Data Index: 1682050 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1573646 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9937. Min Act: -0.0000

Data Index: 1257710 (The Pile)

Max Activating Token Index: 404

Text #8

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9814. Min Act: -0.0000

Data Index: 995655 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1905248 (The Pile)

Max Activating Token Index: 728

Text #10

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9158. Min Act: -0.0000

Data Index: 787000 (The Pile)

Max Activating Token Index: 663

Text #11

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9756. Min Act: -0.0000

Data Index: 202250 (The Pile)

Max Activating Token Index: 224

Text #12

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1232448 (The Pile)

Max Activating Token Index: 419

Text #13

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9033. Min Act: -0.0000

Data Index: 348284 (The Pile)

Max Activating Token Index: 199

Text #14

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1648031 (The Pile)

Max Activating Token Index: 642

Text #15

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1019690 (The Pile)

Max Activating Token Index: 305

Text #16

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.8880. Min Act: -0.0000

Data Index: 1125138 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1700613 (The Pile)

Max Activating Token Index: 684

Text #18

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9121. Min Act: -0.0000

Data Index: 1029330 (The Pile)

Max Activating Token Index: 845

Text #19

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1509512 (The Pile)

Max Activating Token Index: 256