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

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

Neuron 490 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: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0002

Data Index: 791772 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1641521 (Python Code)

Max Activating Token Index: 405

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0119. Min Act: -0.0002

Data Index: 941712 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0118. Min Act: -0.0002

Data Index: 820210 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0002

Data Index: 302456 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0002

Data Index: 115582 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0117. Min Act: -0.0002

Data Index: 824994 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1269449 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1334933 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1036247 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0002

Data Index: 255061 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0002

Data Index: 320466 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0002

Data Index: 47786 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0002

Data Index: 607466 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0002

Data Index: 889516 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0107. Min Act: -0.0002

Data Index: 737922 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0002

Data Index: 814474 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0002

Data Index: 979516 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0002

Data Index: 1388693 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0108. Min Act: -0.0002

Data Index: 121846 (C4 (Web Text))

Max Activating Token Index: 98