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

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

Neuron 80 in Layer 1

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: 0.7159. Min Act: -0.0002

Data Index: 120708 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.7096. Min Act: -0.0002

Data Index: 446608 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.7002. Min Act: -0.0003

Data Index: 434399 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6762. Min Act: -0.0002

Data Index: 1254882 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6145. Min Act: -0.0002

Data Index: 379370 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6001. Min Act: -0.0002

Data Index: 984973 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6012. Min Act: -0.0002

Data Index: 644554 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.5816. Min Act: -0.0002

Data Index: 723193 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.5724. Min Act: -0.0002

Data Index: 441951 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.5635. Min Act: -0.0002

Data Index: 780794 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.5857. Min Act: -0.0002

Data Index: 82629 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.5750. Min Act: -0.0002

Data Index: 821123 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.5582. Min Act: -0.0002

Data Index: 52610 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.5581. Min Act: -0.0002

Data Index: 411739 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.5530. Min Act: -0.0002

Data Index: 292939 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.5642. Min Act: -0.0002

Data Index: 752726 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.5699. Min Act: -0.0002

Data Index: 394626 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.5752. Min Act: -0.0002

Data Index: 1129188 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.5625. Min Act: -0.0002

Data Index: 231382 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.5588. Min Act: -0.0002

Data Index: 661155 (C4 (Web Text))

Max Activating Token Index: 372