Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3564 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0026. Min Act: -0.0001

Data Index: 26333 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0027. Min Act: -0.0001

Data Index: 82204 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0025. Min Act: -0.0001

Data Index: 1009538 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0022. Min Act: -0.0001

Data Index: 867109 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0021. Min Act: -0.0001

Data Index: 1466918 (Python Code)

Max Activating Token Index: 502

Text #5

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0020. Min Act: -0.0001

Data Index: 102984 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0020. Min Act: -0.0001

Data Index: 30684 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0020. Min Act: -0.0001

Data Index: 1058497 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0019. Min Act: -0.0001

Data Index: 191302 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0018. Min Act: -0.0001

Data Index: 1077615 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0019. Min Act: -0.0001

Data Index: 548669 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0019. Min Act: -0.0001

Data Index: 605511 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0019. Min Act: -0.0001

Data Index: 753385 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0019. Min Act: -0.0001

Data Index: 105132 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0018. Min Act: -0.0001

Data Index: 712426 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0019. Min Act: -0.0001

Data Index: 543387 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0018. Min Act: -0.0001

Data Index: 332214 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0020. Min Act: -0.0001

Data Index: 796062 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0018. Min Act: -0.0001

Data Index: 95744 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0018. Min Act: -0.0001

Data Index: 540683 (C4 (Web Text))

Max Activating Token Index: 590