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

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

Neuron 574 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0117. Min Act: -0.0006

Data Index: 850667 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1185973 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0096. Min Act: -0.0006

Data Index: 792355 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0095. Min Act: -0.0006

Data Index: 986882 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0089. Min Act: -0.0006

Data Index: 170951 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0090. Min Act: -0.0006

Data Index: 979615 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0090. Min Act: -0.0006

Data Index: 431494 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0091. Min Act: -0.0006

Data Index: 233704 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0089. Min Act: -0.0006

Data Index: 109147 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0090. Min Act: -0.0006

Data Index: 841274 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0088. Min Act: -0.0006

Data Index: 533814 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0085. Min Act: -0.0006

Data Index: 825255 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0087. Min Act: -0.0006

Data Index: 16218 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1049669 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0083. Min Act: -0.0006

Data Index: 815772 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0083. Min Act: -0.0006

Data Index: 362100 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0084. Min Act: -0.0006

Data Index: 398181 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0084. Min Act: -0.0006

Data Index: 861447 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0082. Min Act: -0.0006

Data Index: 556233 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0081. Min Act: -0.0006

Data Index: 506072 (C4 (Web Text))

Max Activating Token Index: 438