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

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

Neuron 1986 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.9057. Min Act: -0.0001

Data Index: 661377 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.8236. Min Act: -0.0001

Data Index: 222300 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.8170. Min Act: -0.0001

Data Index: 545732 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.7896. Min Act: -0.0001

Data Index: 589472 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.7680. Min Act: -0.0001

Data Index: 31981 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.7982. Min Act: -0.0001

Data Index: 1319276 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.8252. Min Act: -0.0000

Data Index: 244684 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.7189. Min Act: -0.0001

Data Index: 554080 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.7459. Min Act: -0.0000

Data Index: 996996 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.7654. Min Act: -0.0001

Data Index: 1063503 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.7308. Min Act: -0.0001

Data Index: 324580 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.7133. Min Act: -0.0001

Data Index: 627709 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.6776. Min Act: -0.0001

Data Index: 516485 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.7749. Min Act: -0.0001

Data Index: 1067870 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.7076. Min Act: -0.0001

Data Index: 470655 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.7009. Min Act: -0.0000

Data Index: 373243 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.6765. Min Act: -0.0001

Data Index: 1321318 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.7363. Min Act: -0.0001

Data Index: 1303725 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.7098. Min Act: -0.0001

Data Index: 867882 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.9057. Min Range: -0.9057

Max Act: 0.6792. Min Act: -0.0001

Data Index: 1012723 (C4 (Web Text))

Max Activating Token Index: 379