Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3645 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0115. Min Act: -0.0003

Data Index: 797333 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0112. Min Act: -0.0003

Data Index: 845684 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0110. Min Act: -0.0003

Data Index: 181758 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0109. Min Act: -0.0003

Data Index: 789627 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0108. Min Act: -0.0003

Data Index: 674318 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0106. Min Act: -0.0002

Data Index: 807381 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0105. Min Act: -0.0002

Data Index: 429439 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0104. Min Act: -0.0003

Data Index: 475650 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0102. Min Act: -0.0002

Data Index: 1044263 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0101. Min Act: -0.0003

Data Index: 478745 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0100. Min Act: -0.0002

Data Index: 64542 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0099. Min Act: -0.0003

Data Index: 1347885 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0098. Min Act: -0.0003

Data Index: 1006414 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1587498 (Python Code)

Max Activating Token Index: 111

Text #14

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1386576 (Python Code)

Max Activating Token Index: 146

Text #15

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0095. Min Act: -0.0003

Data Index: 177999 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0095. Min Act: -0.0002

Data Index: 52498 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1349461 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0093. Min Act: -0.0003

Data Index: 162203 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0093. Min Act: -0.0003

Data Index: 174045 (C4 (Web Text))

Max Activating Token Index: 704