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

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

Neuron 1601 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: 0.0089. Min Range: -0.0089

Max Act: 0.0089. Min Act: -0.0006

Data Index: 391954 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0089. Min Act: -0.0006

Data Index: 263963 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1147067 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1320052 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0087. Min Act: -0.0006

Data Index: 1014247 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0086. Min Act: -0.0006

Data Index: 956555 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0084. Min Act: -0.0006

Data Index: 613907 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1165514 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0080. Min Act: -0.0006

Data Index: 644501 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0082. Min Act: -0.0006

Data Index: 737757 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0081. Min Act: -0.0006

Data Index: 878303 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1086877 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0080. Min Act: -0.0006

Data Index: 1233907 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0080. Min Act: -0.0006

Data Index: 437626 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0079. Min Act: -0.0006

Data Index: 925213 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0079. Min Act: -0.0006

Data Index: 1449245 (Python Code)

Max Activating Token Index: 873

Text #16

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0079. Min Act: -0.0006

Data Index: 587339 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0080. Min Act: -0.0006

Data Index: 672052 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0079. Min Act: -0.0006

Data Index: 265428 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0079. Min Act: -0.0006

Data Index: 934146 (C4 (Web Text))

Max Activating Token Index: 780