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

Dataset: The Pile

Neuron 1821 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1435194 (The Pile)

Max Activating Token Index: 858

Text #1

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1683330 (The Pile)

Max Activating Token Index: 924

Text #2

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1935132 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5544. Min Act: -0.0000

Data Index: 511004 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1734201 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1925895 (The Pile)

Max Activating Token Index: 648

Text #6

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5512. Min Act: 0.0000

Data Index: 51968 (The Pile)

Max Activating Token Index: 632

Text #7

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1908093 (The Pile)

Max Activating Token Index: 784

Text #8

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5531. Min Act: -0.0000

Data Index: 1461379 (The Pile)

Max Activating Token Index: 865

Text #9

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5171. Min Act: -0.0000

Data Index: 1496618 (The Pile)

Max Activating Token Index: 898

Text #10

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1631896 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5272. Min Act: -0.0000

Data Index: 309834 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1412666 (The Pile)

Max Activating Token Index: 413

Text #13

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5240. Min Act: 0.0000

Data Index: 1072521 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5217. Min Act: -0.0000

Data Index: 317104 (The Pile)

Max Activating Token Index: 555

Text #15

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5248. Min Act: -0.0000

Data Index: 393188 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5057. Min Act: -0.0000

Data Index: 773154 (The Pile)

Max Activating Token Index: 950

Text #17

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1452537 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5019. Min Act: 0.0001

Data Index: 1297986 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5171. Min Act: 0.0000

Data Index: 564096 (The Pile)

Max Activating Token Index: 142