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

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

Neuron 2821 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0093. Min Act: -0.0002

Data Index: 9455 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0094. Min Act: -0.0002

Data Index: 895717 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0093. Min Act: -0.0002

Data Index: 351052 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0091. Min Act: -0.0002

Data Index: 517658 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0093. Min Act: -0.0002

Data Index: 278576 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0092. Min Act: -0.0002

Data Index: 668615 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0094. Min Act: -0.0002

Data Index: 39114 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0092. Min Act: -0.0002

Data Index: 994835 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0092. Min Act: -0.0002

Data Index: 746415 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0092. Min Act: -0.0002

Data Index: 571092 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0092. Min Act: -0.0002

Data Index: 323295 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0091. Min Act: -0.0002

Data Index: 1009774 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1274900 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0091. Min Act: -0.0002

Data Index: 462930 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0089. Min Act: -0.0002

Data Index: 999453 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0091. Min Act: -0.0002

Data Index: 312843 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0091. Min Act: -0.0002

Data Index: 288630 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0090. Min Act: -0.0002

Data Index: 241150 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0090. Min Act: -0.0002

Data Index: 800954 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0090. Min Act: -0.0002

Data Index: 163138 (C4 (Web Text))

Max Activating Token Index: 27