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

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

Neuron 23 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: 0.0148. Min Range: -0.0148

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1144222 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0111. Min Act: -0.0002

Data Index: 539850 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0110. Min Act: -0.0002

Data Index: 970841 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0107. Min Act: -0.0002

Data Index: 299801 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0105. Min Act: -0.0002

Data Index: 843917 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0104. Min Act: -0.0002

Data Index: 445253 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1297399 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0102. Min Act: -0.0002

Data Index: 1229740 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0101. Min Act: -0.0002

Data Index: 1062329 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0099. Min Act: -0.0002

Data Index: 100566 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0098. Min Act: -0.0002

Data Index: 222031 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1616221 (Python Code)

Max Activating Token Index: 294

Text #12

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1338546 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1530319 (Python Code)

Max Activating Token Index: 149

Text #14

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0095. Min Act: -0.0002

Data Index: 317193 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1393406 (Python Code)

Max Activating Token Index: 109

Text #16

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0090. Min Act: -0.0002

Data Index: 140972 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0091. Min Act: -0.0002

Data Index: 47718 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0091. Min Act: -0.0002

Data Index: 919970 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0091. Min Act: -0.0002

Data Index: 696154 (C4 (Web Text))

Max Activating Token Index: 699