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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4306 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6892. Min Range: -3.6892

Max Act: 3.6892. Min Act: -0.0000

Data Index: 1164285 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 3.6892. Min Range: -3.6892

Max Act: 3.3056. Min Act: -0.0000

Data Index: 661376 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.8527. Min Act: -0.0000

Data Index: 1291738 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.8528. Min Act: -0.0000

Data Index: 1212404 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.5229. Min Act: -0.0000

Data Index: 332867 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.6782. Min Act: -0.0000

Data Index: 382726 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.6717. Min Act: -0.0000

Data Index: 247016 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.2386. Min Act: -0.0000

Data Index: 54559 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.3628. Min Act: -0.0000

Data Index: 958539 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.3345. Min Act: -0.0000

Data Index: 767766 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.3348. Min Act: -0.0000

Data Index: 929693 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.2597. Min Act: -0.0000

Data Index: 1315790 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 3.6892. Min Range: -3.6892

Max Act: 1.9956. Min Act: -0.0000

Data Index: 1150576 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.1629. Min Act: -0.0000

Data Index: 68729 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.0821. Min Act: -0.0000

Data Index: 746292 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.1269. Min Act: -0.0000

Data Index: 831451 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.1491. Min Act: -0.0000

Data Index: 303780 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.1003. Min Act: -0.0000

Data Index: 942809 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 3.6892. Min Range: -3.6892

Max Act: 2.0707. Min Act: -0.0000

Data Index: 299171 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 3.6892. Min Range: -3.6892

Max Act: 1.9094. Min Act: -0.0000

Data Index: 1217292 (C4 (Web Text))

Max Activating Token Index: 650