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

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

Neuron 973 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: 0.0133. Min Range: -0.0133

Max Act: 0.0133. Min Act: -0.0006

Data Index: 4065 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0118. Min Act: -0.0006

Data Index: 437509 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1329456 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0117. Min Act: -0.0006

Data Index: 550820 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0111. Min Act: -0.0006

Data Index: 16615 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0108. Min Act: -0.0006

Data Index: 636109 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0107. Min Act: -0.0006

Data Index: 794298 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1173277 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0106. Min Act: -0.0006

Data Index: 722481 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0108. Min Act: -0.0006

Data Index: 742214 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0106. Min Act: -0.0006

Data Index: 208081 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1636615 (Python Code)

Max Activating Token Index: 794

Text #12

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0106. Min Act: -0.0006

Data Index: 428273 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0103. Min Act: -0.0006

Data Index: 497865 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0105. Min Act: -0.0006

Data Index: 395868 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0108. Min Act: -0.0006

Data Index: 269596 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1220551 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0104. Min Act: -0.0006

Data Index: 771771 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1598863 (Python Code)

Max Activating Token Index: 210

Text #19

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1416873 (Python Code)

Max Activating Token Index: 8