Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1025 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1170253 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0114. Min Act: -0.0006

Data Index: 694278 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0109. Min Act: -0.0006

Data Index: 524386 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0113. Min Act: -0.0005

Data Index: 530901 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0108. Min Act: -0.0006

Data Index: 125527 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1126234 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1060162 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0107. Min Act: -0.0006

Data Index: 113500 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1138820 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0106. Min Act: -0.0006

Data Index: 838970 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0104. Min Act: -0.0006

Data Index: 995463 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0106. Min Act: -0.0007

Data Index: 943754 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0106. Min Act: -0.0007

Data Index: 674350 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0106. Min Act: -0.0007

Data Index: 1046721 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0105. Min Act: -0.0006

Data Index: 355050 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0104. Min Act: -0.0006

Data Index: 561015 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1092046 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1381462 (Python Code)

Max Activating Token Index: 843

Text #18

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0100. Min Act: -0.0006

Data Index: 84611 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0102. Min Act: -0.0006

Data Index: 764833 (C4 (Web Text))

Max Activating Token Index: 329