Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 918 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.1048. Min Act: -0.0006

Data Index: 56191 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0959. Min Act: -0.0006

Data Index: 298375 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0990. Min Act: -0.0006

Data Index: 38492 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0943. Min Act: -0.0006

Data Index: 1209488 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0940. Min Act: -0.0006

Data Index: 1090233 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0931. Min Act: -0.0006

Data Index: 911656 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0960. Min Act: -0.0006

Data Index: 427425 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0949. Min Act: -0.0006

Data Index: 826176 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0907. Min Act: -0.0006

Data Index: 111378 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0906. Min Act: -0.0006

Data Index: 229594 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0938. Min Act: -0.0006

Data Index: 1106663 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0937. Min Act: -0.0006

Data Index: 145458 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0938. Min Act: -0.0006

Data Index: 752450 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0955. Min Act: -0.0006

Data Index: 1356195 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0910. Min Act: -0.0006

Data Index: 92556 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0910. Min Act: -0.0006

Data Index: 66678 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0906. Min Act: -0.0006

Data Index: 403931 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0908. Min Act: -0.0006

Data Index: 468898 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0905. Min Act: -0.0006

Data Index: 1335205 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0868. Min Act: -0.0006

Data Index: 307348 (C4 (Web Text))

Max Activating Token Index: 971