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

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

Neuron 2500 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3007. Min Act: -0.0001

Data Index: 653282 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3334. Min Act: -0.0001

Data Index: 1165142 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3740. Min Act: -0.0001

Data Index: 564942 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3155. Min Act: -0.0001

Data Index: 75701 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3115. Min Act: -0.0000

Data Index: 355813 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2812. Min Act: -0.0000

Data Index: 1010484 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2782. Min Act: -0.0001

Data Index: 592313 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2889. Min Act: -0.0000

Data Index: 445815 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2673. Min Act: -0.0001

Data Index: 304173 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3138. Min Act: -0.0001

Data Index: 266593 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2928. Min Act: -0.0000

Data Index: 157303 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3017. Min Act: -0.0001

Data Index: 552446 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2798. Min Act: -0.0001

Data Index: 841702 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2446. Min Act: -0.0001

Data Index: 327675 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2685. Min Act: -0.0001

Data Index: 486631 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2750. Min Act: -0.0001

Data Index: 947851 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.3015. Min Act: -0.0001

Data Index: 702118 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2769. Min Act: -0.0001

Data Index: 209335 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2517. Min Act: -0.0001

Data Index: 131687 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.3740. Min Range: -0.3740

Max Act: 0.2732. Min Act: -0.0001

Data Index: 960952 (C4 (Web Text))

Max Activating Token Index: 362