Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 866 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1280. Min Act: -0.0002

Data Index: 47783 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1245. Min Act: -0.0002

Data Index: 86120 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1155. Min Act: -0.0002

Data Index: 510012 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1270220 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1119. Min Act: -0.0002

Data Index: 1290865 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1265896 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1052. Min Act: -0.0002

Data Index: 96675 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1080. Min Act: -0.0002

Data Index: 639333 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1063. Min Act: -0.0002

Data Index: 12821 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1003239 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1027. Min Act: -0.0002

Data Index: 1115516 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1001. Min Act: -0.0002

Data Index: 1253419 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0974. Min Act: -0.0002

Data Index: 848221 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0984. Min Act: -0.0001

Data Index: 454258 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0996. Min Act: -0.0002

Data Index: 142499 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1043605 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1003. Min Act: -0.0002

Data Index: 516022 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0958. Min Act: -0.0002

Data Index: 785162 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1335550 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0938. Min Act: -0.0002

Data Index: 397382 (C4 (Web Text))

Max Activating Token Index: 840