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

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

Neuron 174 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5778. Min Act: -0.0002

Data Index: 514253 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.4197. Min Act: -0.0002

Data Index: 1077015 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.4821. Min Act: -0.0002

Data Index: 54946 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5083. Min Act: -0.0002

Data Index: 640498 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.3666. Min Act: -0.0002

Data Index: 644736 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.3050. Min Act: -0.0002

Data Index: 806647 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.4297. Min Act: -0.0002

Data Index: 1319556 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.3801. Min Act: -0.0002

Data Index: 668927 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.3640. Min Act: -0.0002

Data Index: 674858 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.2346. Min Act: -0.0002

Data Index: 466870 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.1682. Min Act: -0.0002

Data Index: 498165 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.2048. Min Act: -0.0002

Data Index: 891293 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.0754. Min Act: -0.0002

Data Index: 40227 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.2143. Min Act: -0.0002

Data Index: 1029091 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.2946. Min Act: -0.0002

Data Index: 131225 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.2811. Min Act: -0.0002

Data Index: 574175 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.3297. Min Act: -0.0002

Data Index: 1054742 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.2929. Min Act: -0.0002

Data Index: 806120 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.3538. Min Act: -0.0002

Data Index: 481908 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.2241. Min Act: -0.0002

Data Index: 1240141 (C4 (Web Text))

Max Activating Token Index: 564