Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2379 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1271452 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1199242 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1310. Min Act: -0.0001

Data Index: 139908 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1280. Min Act: -0.0001

Data Index: 1029449 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1233. Min Act: -0.0001

Data Index: 744255 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1268. Min Act: -0.0001

Data Index: 654396 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1234. Min Act: -0.0001

Data Index: 369946 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1189. Min Act: -0.0001

Data Index: 110807 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1189. Min Act: -0.0001

Data Index: 26234 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1111. Min Act: -0.0001

Data Index: 595127 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1084127 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1089. Min Act: -0.0001

Data Index: 126123 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1163814 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1016. Min Act: -0.0001

Data Index: 267747 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1098. Min Act: -0.0001

Data Index: 755350 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0974. Min Act: -0.0001

Data Index: 235848 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1204. Min Act: -0.0001

Data Index: 536931 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1003. Min Act: -0.0001

Data Index: 1552808 (Python Code)

Max Activating Token Index: 362

Text #18

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0997. Min Act: -0.0001

Data Index: 759578 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1139. Min Act: -0.0001

Data Index: 51364 (C4 (Web Text))

Max Activating Token Index: 833