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

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

Neuron 970 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0248. Min Act: -0.0005

Data Index: 576870 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0129. Min Act: -0.0005

Data Index: 1233064 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0128. Min Act: -0.0005

Data Index: 1248744 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0121. Min Act: -0.0005

Data Index: 111878 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1073341 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0118. Min Act: -0.0005

Data Index: 375974 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0118. Min Act: -0.0005

Data Index: 428418 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0125. Min Act: -0.0005

Data Index: 25109 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0128. Min Act: -0.0005

Data Index: 1042411 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0122. Min Act: -0.0005

Data Index: 538932 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0095. Min Act: -0.0005

Data Index: 799191 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0125. Min Act: -0.0005

Data Index: 371737 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0115. Min Act: -0.0005

Data Index: 255846 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0122. Min Act: -0.0005

Data Index: 649201 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0119. Min Act: -0.0005

Data Index: 1308863 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0114. Min Act: -0.0005

Data Index: 650755 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0122. Min Act: -0.0005

Data Index: 88779 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0120. Min Act: -0.0005

Data Index: 1133677 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0113. Min Act: -0.0005

Data Index: 673353 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0116. Min Act: -0.0005

Data Index: 670380 (C4 (Web Text))

Max Activating Token Index: 404