Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1930 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.8811. Min Act: -0.0002

Data Index: 1293058 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.8175. Min Act: -0.0002

Data Index: 11894 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.7076. Min Act: -0.0002

Data Index: 734697 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.6573. Min Act: -0.0002

Data Index: 892420 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.6547. Min Act: -0.0002

Data Index: 640696 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.5818. Min Act: -0.0002

Data Index: 745118 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.5917. Min Act: -0.0002

Data Index: 144499 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.6245. Min Act: -0.0002

Data Index: 1149634 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.6351. Min Act: -0.0002

Data Index: 100995 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.5218. Min Act: -0.0002

Data Index: 855435 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.5937. Min Act: -0.0002

Data Index: 1000304 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.5136. Min Act: -0.0002

Data Index: 1232282 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.5186. Min Act: -0.0002

Data Index: 714381 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.5908. Min Act: -0.0002

Data Index: 692288 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.5128. Min Act: -0.0002

Data Index: 1206555 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.4869. Min Act: -0.0002

Data Index: 1055001 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.4781. Min Act: -0.0002

Data Index: 371051 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.4159. Min Act: -0.0002

Data Index: 1238693 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.4290. Min Act: -0.0002

Data Index: 1013218 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.4365. Min Act: -0.0002

Data Index: 780263 (C4 (Web Text))

Max Activating Token Index: 1010