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

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

Neuron 4102 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0125. Min Range: -1.0125

Max Act: 1.0125. Min Act: -0.0001

Data Index: 119183 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8809. Min Act: -0.0001

Data Index: 410580 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7865. Min Act: -0.0001

Data Index: 5670 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8962. Min Act: -0.0001

Data Index: 27820 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7757. Min Act: -0.0001

Data Index: 59030 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8242. Min Act: -0.0001

Data Index: 886231 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7388. Min Act: -0.0001

Data Index: 137780 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.6026. Min Act: -0.0001

Data Index: 1240948 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7177. Min Act: -0.0001

Data Index: 134549 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7171. Min Act: -0.0001

Data Index: 1123923 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7109. Min Act: -0.0001

Data Index: 390832 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.6849. Min Act: -0.0001

Data Index: 247356 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.6071. Min Act: -0.0001

Data Index: 339125 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7257. Min Act: -0.0001

Data Index: 929031 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.6558. Min Act: -0.0001

Data Index: 1085856 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.6853. Min Act: -0.0001

Data Index: 403777 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.6585. Min Act: -0.0001

Data Index: 767287 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.6542. Min Act: -0.0001

Data Index: 451465 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7205. Min Act: -0.0001

Data Index: 693671 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.6650. Min Act: -0.0001

Data Index: 920614 (C4 (Web Text))

Max Activating Token Index: 262