Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 153 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1308751 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1046885 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0124. Min Act: -0.0002

Data Index: 521662 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0118. Min Act: -0.0002

Data Index: 139913 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0109. Min Act: -0.0002

Data Index: 908324 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0106. Min Act: -0.0002

Data Index: 964503 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0104. Min Act: -0.0002

Data Index: 452749 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0100. Min Act: -0.0002

Data Index: 692455 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0093. Min Act: -0.0002

Data Index: 845886 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0094. Min Act: -0.0002

Data Index: 34316 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1038896 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1139232 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0095. Min Act: -0.0002

Data Index: 1325611 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0093. Min Act: -0.0002

Data Index: 554602 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0093. Min Act: -0.0002

Data Index: 951956 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1145117 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1317476 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0087. Min Act: -0.0002

Data Index: 516043 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1121081 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1273972 (C4 (Web Text))

Max Activating Token Index: 308