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

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

Neuron 1720 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: 0.0117. Min Range: -0.0117

Max Act: 0.0117. Min Act: -0.0006

Data Index: 68279 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0113. Min Act: -0.0005

Data Index: 943462 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0114. Min Act: -0.0006

Data Index: 973002 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0110. Min Act: -0.0005

Data Index: 48506 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0106. Min Act: -0.0006

Data Index: 216999 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0103. Min Act: -0.0006

Data Index: 137505 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0098. Min Act: -0.0006

Data Index: 357161 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0100. Min Act: -0.0006

Data Index: 639653 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0100. Min Act: -0.0005

Data Index: 113955 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0099. Min Act: -0.0006

Data Index: 455262 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1065217 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0097. Min Act: -0.0006

Data Index: 624341 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0097. Min Act: -0.0006

Data Index: 100810 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0095. Min Act: -0.0006

Data Index: 946244 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0093. Min Act: -0.0006

Data Index: 329019 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0094. Min Act: -0.0006

Data Index: 473846 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1111182 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0094. Min Act: -0.0005

Data Index: 341644 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0092. Min Act: -0.0006

Data Index: 583356 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1168236 (C4 (Web Text))

Max Activating Token Index: 254