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

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

Neuron 3820 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: 0.0098. Min Range: -0.0098

Max Act: 0.0098. Min Act: -0.0002

Data Index: 945921 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1308850 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0095. Min Act: -0.0002

Data Index: 570299 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0093. Min Act: -0.0002

Data Index: 945662 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1035581 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0089. Min Act: -0.0002

Data Index: 481627 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0091. Min Act: -0.0002

Data Index: 1371667 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0091. Min Act: -0.0002

Data Index: 678954 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0090. Min Act: -0.0002

Data Index: 799006 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1193302 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0088. Min Act: -0.0002

Data Index: 800240 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1264605 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1286910 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1031125 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0089. Min Act: -0.0002

Data Index: 913556 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0089. Min Act: -0.0002

Data Index: 886583 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0089. Min Act: -0.0002

Data Index: 879486 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0089. Min Act: -0.0002

Data Index: 618349 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0087. Min Act: -0.0002

Data Index: 144095 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0088. Min Act: -0.0002

Data Index: 421886 (C4 (Web Text))

Max Activating Token Index: 532