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

Dataset: The Pile

Neuron 69 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.4595. Min Range: -8.4595

Max Act: 7.7569. Min Act: -0.0000

Data Index: 1794038 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 8.4595. Min Range: -8.4595

Max Act: 7.7569. Min Act: -0.0000

Data Index: 47795 (The Pile)

Max Activating Token Index: 345

Text #2

Max Range: 8.4595. Min Range: -8.4595

Max Act: 8.4595. Min Act: -0.0000

Data Index: 17390 (The Pile)

Max Activating Token Index: 952

Text #3

Max Range: 8.4595. Min Range: -8.4595

Max Act: 4.2492. Min Act: -0.0000

Data Index: 344756 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 8.4595. Min Range: -8.4595

Max Act: 5.6074. Min Act: -0.0000

Data Index: 1423933 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 8.4595. Min Range: -8.4595

Max Act: 4.9011. Min Act: -0.0000

Data Index: 1732144 (The Pile)

Max Activating Token Index: 757

Text #6

Max Range: 8.4595. Min Range: -8.4595

Max Act: 4.8203. Min Act: -0.0000

Data Index: 90527 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 8.4595. Min Range: -8.4595

Max Act: 3.9544. Min Act: -0.0000

Data Index: 1136651 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 8.4595. Min Range: -8.4595

Max Act: 2.8005. Min Act: -0.0000

Data Index: 1423693 (The Pile)

Max Activating Token Index: 682

Text #9

Max Range: 8.4595. Min Range: -8.4595

Max Act: 3.7428. Min Act: -0.0000

Data Index: 343053 (The Pile)

Max Activating Token Index: 658

Text #10

Max Range: 8.4595. Min Range: -8.4595

Max Act: 3.8297. Min Act: -0.0000

Data Index: 50666 (The Pile)

Max Activating Token Index: 504

Text #11

Max Range: 8.4595. Min Range: -8.4595

Max Act: 3.0694. Min Act: -0.0000

Data Index: 1400928 (The Pile)

Max Activating Token Index: 575

Text #12

Max Range: 8.4595. Min Range: -8.4595

Max Act: 2.8412. Min Act: -0.0000

Data Index: 1015975 (The Pile)

Max Activating Token Index: 93

Text #13

Max Range: 8.4595. Min Range: -8.4595

Max Act: 2.0505. Min Act: -0.0000

Data Index: 100082 (The Pile)

Max Activating Token Index: 161

Text #14

Max Range: 8.4595. Min Range: -8.4595

Max Act: 3.0375. Min Act: -0.0000

Data Index: 1232132 (The Pile)

Max Activating Token Index: 646

Text #15

Max Range: 8.4595. Min Range: -8.4595

Max Act: 1.8937. Min Act: -0.0000

Data Index: 1541028 (The Pile)

Max Activating Token Index: 755

Text #16

Max Range: 8.4595. Min Range: -8.4595

Max Act: 2.3414. Min Act: -0.0000

Data Index: 1195903 (The Pile)

Max Activating Token Index: 857

Text #17

Max Range: 8.4595. Min Range: -8.4595

Max Act: 1.2853. Min Act: -0.0000

Data Index: 721764 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 8.4595. Min Range: -8.4595

Max Act: 2.7167. Min Act: -0.0000

Data Index: 1536248 (The Pile)

Max Activating Token Index: 508

Text #19

Max Range: 8.4595. Min Range: -8.4595

Max Act: 2.0684. Min Act: -0.0000

Data Index: 393182 (The Pile)

Max Activating Token Index: 44