Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 505 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0142. Min Act: -0.0005

Data Index: 734147 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0135. Min Act: -0.0005

Data Index: 788266 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0128. Min Act: -0.0005

Data Index: 851621 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0126. Min Act: -0.0005

Data Index: 794801 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0121. Min Act: -0.0005

Data Index: 1004465 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0120. Min Act: -0.0005

Data Index: 10762 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0112. Min Act: -0.0005

Data Index: 916991 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0115. Min Act: -0.0005

Data Index: 645818 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0111. Min Act: -0.0005

Data Index: 601248 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0114. Min Act: -0.0005

Data Index: 499561 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0113. Min Act: -0.0005

Data Index: 1085892 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0111. Min Act: -0.0005

Data Index: 653090 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0111. Min Act: -0.0005

Data Index: 618243 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0115. Min Act: -0.0005

Data Index: 615109 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1336640 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0108. Min Act: -0.0005

Data Index: 12825 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0108. Min Act: -0.0005

Data Index: 1174833 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0110. Min Act: -0.0005

Data Index: 800812 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0108. Min Act: -0.0005

Data Index: 177312 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0107. Min Act: -0.0006

Data Index: 587348 (C4 (Web Text))

Max Activating Token Index: 631