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

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

Neuron 5073 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0114. Min Act: -0.0001

Data Index: 677489 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0113. Min Act: -0.0001

Data Index: 1309357 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0107. Min Act: -0.0001

Data Index: 663912 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0103. Min Act: -0.0001

Data Index: 1312822 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0106. Min Act: -0.0001

Data Index: 809400 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0104. Min Act: -0.0001

Data Index: 747219 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0098. Min Act: -0.0001

Data Index: 1180115 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0096. Min Act: -0.0001

Data Index: 498140 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0099. Min Act: -0.0001

Data Index: 1176563 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0093. Min Act: -0.0001

Data Index: 674541 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0090. Min Act: -0.0001

Data Index: 1395830 (Python Code)

Max Activating Token Index: 859

Text #11

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0091. Min Act: -0.0001

Data Index: 863847 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0095. Min Act: -0.0001

Data Index: 1182527 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0096. Min Act: -0.0001

Data Index: 314267 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0091. Min Act: -0.0001

Data Index: 1150401 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0088. Min Act: -0.0001

Data Index: 186443 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0090. Min Act: -0.0001

Data Index: 747688 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0087. Min Act: -0.0001

Data Index: 539596 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0090. Min Act: -0.0001

Data Index: 1206979 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0089. Min Act: -0.0001

Data Index: 676728 (C4 (Web Text))

Max Activating Token Index: 23