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

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

Neuron 4760 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: 1.2972. Min Range: -1.2972

Max Act: 1.2362. Min Act: -0.0001

Data Index: 368051 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 1.2972. Min Range: -1.2972

Max Act: 1.2079. Min Act: -0.0001

Data Index: 137595 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 1.2972. Min Range: -1.2972

Max Act: 1.2972. Min Act: -0.0001

Data Index: 383997 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 1.2972. Min Range: -1.2972

Max Act: 1.0887. Min Act: -0.0001

Data Index: 183903 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 1.2972. Min Range: -1.2972

Max Act: 0.9980. Min Act: -0.0001

Data Index: 576044 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 1.2972. Min Range: -1.2972

Max Act: 1.0111. Min Act: -0.0001

Data Index: 1294678 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 1.2972. Min Range: -1.2972

Max Act: 1.0669. Min Act: -0.0001

Data Index: 313087 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 1.2972. Min Range: -1.2972

Max Act: 1.0687. Min Act: -0.0001

Data Index: 1109923 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 1.2972. Min Range: -1.2972

Max Act: 1.0976. Min Act: -0.0001

Data Index: 666063 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 1.2972. Min Range: -1.2972

Max Act: 0.9689. Min Act: -0.0001

Data Index: 790874 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 1.2972. Min Range: -1.2972

Max Act: 1.0222. Min Act: -0.0001

Data Index: 1220822 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 1.2972. Min Range: -1.2972

Max Act: 1.2053. Min Act: -0.0001

Data Index: 393156 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 1.2972. Min Range: -1.2972

Max Act: 1.0004. Min Act: -0.0001

Data Index: 937277 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 1.2972. Min Range: -1.2972

Max Act: 0.9838. Min Act: -0.0001

Data Index: 707370 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 1.2972. Min Range: -1.2972

Max Act: 1.0125. Min Act: -0.0001

Data Index: 544976 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 1.2972. Min Range: -1.2972

Max Act: 1.0710. Min Act: -0.0001

Data Index: 245753 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 1.2972. Min Range: -1.2972

Max Act: 0.9209. Min Act: -0.0001

Data Index: 216238 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 1.2972. Min Range: -1.2972

Max Act: 0.8574. Min Act: -0.0001

Data Index: 645770 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 1.2972. Min Range: -1.2972

Max Act: 0.8874. Min Act: -0.0001

Data Index: 60826 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 1.2972. Min Range: -1.2972

Max Act: 0.8947. Min Act: -0.0001

Data Index: 161204 (C4 (Web Text))

Max Activating Token Index: 327