Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1583 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0102. Min Act: -0.0005

Data Index: 18635 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0085. Min Act: -0.0006

Data Index: 237819 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1048294 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1147597 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1313743 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1120454 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0076. Min Act: -0.0006

Data Index: 623522 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0074. Min Act: -0.0006

Data Index: 140541 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0071. Min Act: -0.0006

Data Index: 240144 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0074. Min Act: -0.0006

Data Index: 304790 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1476045 (Python Code)

Max Activating Token Index: 700

Text #11

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0071. Min Act: -0.0006

Data Index: 390595 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1396863 (Python Code)

Max Activating Token Index: 802

Text #13

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0075. Min Act: -0.0006

Data Index: 615788 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0073. Min Act: -0.0006

Data Index: 89859 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1129698 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1249554 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1429063 (Python Code)

Max Activating Token Index: 845

Text #18

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1197098 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1463339 (Python Code)

Max Activating Token Index: 340