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

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

Neuron 217 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: 0.7159. Min Range: -0.7159

Max Act: 0.7045. Min Act: -0.0001

Data Index: 1030713 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.7159. Min Act: -0.0001

Data Index: 1192164 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.7071. Min Act: -0.0001

Data Index: 483947 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6944. Min Act: -0.0001

Data Index: 422539 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6850. Min Act: -0.0001

Data Index: 645368 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6992. Min Act: -0.0001

Data Index: 343304 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6950. Min Act: -0.0001

Data Index: 1048753 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6993. Min Act: -0.0001

Data Index: 1035853 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6900. Min Act: -0.0001

Data Index: 1572785 (Python Code)

Max Activating Token Index: 2

Text #9

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6900. Min Act: -0.0001

Data Index: 1570125 (Python Code)

Max Activating Token Index: 2

Text #10

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6772. Min Act: -0.0001

Data Index: 574156 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6985. Min Act: -0.0001

Data Index: 621102 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6985. Min Act: -0.0001

Data Index: 331470 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6985. Min Act: -0.0001

Data Index: 1029211 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6985. Min Act: -0.0001

Data Index: 788899 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6985. Min Act: -0.0001

Data Index: 548884 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6985. Min Act: -0.0001

Data Index: 205842 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6985. Min Act: -0.0001

Data Index: 1069033 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6985. Min Act: -0.0001

Data Index: 474408 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6985. Min Act: -0.0001

Data Index: 1160990 (C4 (Web Text))

Max Activating Token Index: 2