Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4220 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1346888 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1170620 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0893. Min Act: -0.0001

Data Index: 756781 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0892. Min Act: -0.0001

Data Index: 711315 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1246181 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0868. Min Act: -0.0001

Data Index: 643972 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0873. Min Act: -0.0001

Data Index: 142549 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0867. Min Act: -0.0001

Data Index: 566882 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0838. Min Act: -0.0001

Data Index: 840364 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1012154 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0857. Min Act: -0.0001

Data Index: 27215 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0835. Min Act: -0.0001

Data Index: 186617 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0847. Min Act: -0.0001

Data Index: 32464 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0816. Min Act: -0.0001

Data Index: 75749 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0841. Min Act: -0.0001

Data Index: 354850 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0820. Min Act: -0.0001

Data Index: 251833 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0832. Min Act: -0.0001

Data Index: 47270 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0821. Min Act: -0.0001

Data Index: 759294 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0810. Min Act: -0.0001

Data Index: 831378 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0824. Min Act: -0.0001

Data Index: 785950 (C4 (Web Text))

Max Activating Token Index: 904