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

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

Neuron 1870 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: 927599 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0111. Min Act: -0.0006

Data Index: 276831 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1232573 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1240978 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0108. Min Act: -0.0006

Data Index: 1260250 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0110. Min Act: -0.0006

Data Index: 480929 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0109. Min Act: -0.0006

Data Index: 24950 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0108. Min Act: -0.0006

Data Index: 1341822 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0108. Min Act: -0.0006

Data Index: 468947 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0106. Min Act: -0.0005

Data Index: 789858 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1195428 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0105. Min Act: -0.0006

Data Index: 98918 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0104. Min Act: -0.0006

Data Index: 301356 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0104. Min Act: -0.0006

Data Index: 649065 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0103. Min Act: -0.0006

Data Index: 796244 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0105. Min Act: -0.0006

Data Index: 225135 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0103. Min Act: -0.0006

Data Index: 386439 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1305381 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0103. Min Act: -0.0006

Data Index: 223765 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1259672 (C4 (Web Text))

Max Activating Token Index: 830