Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1150 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0110. Min Act: -0.0003

Data Index: 331370 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0106. Min Act: -0.0003

Data Index: 326344 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0106. Min Act: -0.0004

Data Index: 612182 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0103. Min Act: -0.0003

Data Index: 200810 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0105. Min Act: -0.0004

Data Index: 962476 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0101. Min Act: -0.0003

Data Index: 821633 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0099. Min Act: -0.0003

Data Index: 398922 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0099. Min Act: -0.0003

Data Index: 405791 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0099. Min Act: -0.0003

Data Index: 513391 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0097. Min Act: -0.0003

Data Index: 1145485 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0096. Min Act: -0.0003

Data Index: 147535 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0095. Min Act: -0.0003

Data Index: 68978 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0095. Min Act: -0.0004

Data Index: 391659 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0095. Min Act: -0.0004

Data Index: 748950 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0095. Min Act: -0.0004

Data Index: 904198 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0095. Min Act: -0.0003

Data Index: 685848 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0094. Min Act: -0.0004

Data Index: 44748 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0096. Min Act: -0.0004

Data Index: 699343 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0094. Min Act: -0.0003

Data Index: 263907 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0091. Min Act: -0.0003

Data Index: 833561 (C4 (Web Text))

Max Activating Token Index: 669