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

Dataset: The Pile

Neuron 354 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: 0.5807. Min Range: -0.5807

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1149514 (The Pile)

Max Activating Token Index: 487

Text #1

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5582. Min Act: -0.0000

Data Index: 490684 (The Pile)

Max Activating Token Index: 928

Text #2

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5807. Min Act: -0.0000

Data Index: 252457 (The Pile)

Max Activating Token Index: 481

Text #3

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1639198 (The Pile)

Max Activating Token Index: 489

Text #4

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4258. Min Act: -0.0000

Data Index: 177372 (The Pile)

Max Activating Token Index: 482

Text #5

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1084769 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4130. Min Act: -0.0000

Data Index: 920001 (The Pile)

Max Activating Token Index: 992

Text #7

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1405528 (The Pile)

Max Activating Token Index: 216

Text #8

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4052. Min Act: -0.0000

Data Index: 352602 (The Pile)

Max Activating Token Index: 534

Text #9

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3610. Min Act: -0.0000

Data Index: 1512685 (The Pile)

Max Activating Token Index: 640

Text #10

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3999. Min Act: -0.0000

Data Index: 1969336 (The Pile)

Max Activating Token Index: 589

Text #11

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1495943 (The Pile)

Max Activating Token Index: 556

Text #12

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1640472 (The Pile)

Max Activating Token Index: 963

Text #13

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3820. Min Act: -0.0000

Data Index: 1152014 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3811. Min Act: -0.0000

Data Index: 836673 (The Pile)

Max Activating Token Index: 509

Text #15

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1655191 (The Pile)

Max Activating Token Index: 759

Text #16

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3787. Min Act: -0.0000

Data Index: 1244726 (The Pile)

Max Activating Token Index: 138

Text #17

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3524. Min Act: -0.0000

Data Index: 340165 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3894. Min Act: -0.0000

Data Index: 284208 (The Pile)

Max Activating Token Index: 242

Text #19

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3718. Min Act: -0.0000

Data Index: 1984393 (The Pile)

Max Activating Token Index: 500