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

Dataset: The Pile

Neuron 664 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: 0.5079. Min Range: -0.5079

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1834975 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1797155 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1667606 (The Pile)

Max Activating Token Index: 459

Text #3

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1361651 (The Pile)

Max Activating Token Index: 557

Text #4

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1643175 (The Pile)

Max Activating Token Index: 548

Text #5

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1360189 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3858. Min Act: -0.0000

Data Index: 820837 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1642714 (The Pile)

Max Activating Token Index: 522

Text #8

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3604. Min Act: -0.0000

Data Index: 1662422 (The Pile)

Max Activating Token Index: 68

Text #9

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3770. Min Act: -0.0000

Data Index: 568103 (The Pile)

Max Activating Token Index: 770

Text #10

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3821. Min Act: -0.0000

Data Index: 640125 (The Pile)

Max Activating Token Index: 724

Text #11

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4005. Min Act: -0.0000

Data Index: 467349 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1375887 (The Pile)

Max Activating Token Index: 190

Text #13

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1144275 (The Pile)

Max Activating Token Index: 756

Text #14

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3905. Min Act: -0.0000

Data Index: 1684895 (The Pile)

Max Activating Token Index: 261

Text #15

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3506. Min Act: -0.0000

Data Index: 1694647 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4112. Min Act: -0.0000

Data Index: 712439 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3733. Min Act: -0.0000

Data Index: 1740514 (The Pile)

Max Activating Token Index: 411

Text #18

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3644. Min Act: -0.0000

Data Index: 872682 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1945951 (The Pile)

Max Activating Token Index: 319