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

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

Neuron 384 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: 0.0128. Min Range: -0.0128

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1355892 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0128. Min Act: -0.0006

Data Index: 458662 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0123. Min Act: -0.0006

Data Index: 477572 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0123. Min Act: -0.0006

Data Index: 483011 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1269995 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0120. Min Act: -0.0006

Data Index: 443258 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0118. Min Act: -0.0006

Data Index: 979644 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0117. Min Act: -0.0006

Data Index: 36591 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0122. Min Act: -0.0006

Data Index: 445833 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1123912 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0114. Min Act: -0.0006

Data Index: 28900 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0112. Min Act: -0.0006

Data Index: 928248 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0117. Min Act: -0.0006

Data Index: 489366 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0113. Min Act: -0.0006

Data Index: 351813 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0108. Min Act: -0.0006

Data Index: 451917 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0108. Min Act: -0.0006

Data Index: 87499 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0108. Min Act: -0.0006

Data Index: 406846 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0107. Min Act: -0.0006

Data Index: 773901 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0107. Min Act: -0.0006

Data Index: 189953 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1194190 (C4 (Web Text))

Max Activating Token Index: 984