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

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

Neuron 1896 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: 0.0136. Min Range: -0.0136

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1378122 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1528386 (Python Code)

Max Activating Token Index: 212

Text #2

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1376521 (Python Code)

Max Activating Token Index: 310

Text #3

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1438170 (Python Code)

Max Activating Token Index: 130

Text #4

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1601297 (Python Code)

Max Activating Token Index: 302

Text #5

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1474172 (Python Code)

Max Activating Token Index: 25

Text #6

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0121. Min Act: -0.0006

Data Index: 816811 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1552861 (Python Code)

Max Activating Token Index: 336

Text #8

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1650986 (Python Code)

Max Activating Token Index: 143

Text #9

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1619599 (Python Code)

Max Activating Token Index: 78

Text #10

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1467649 (Python Code)

Max Activating Token Index: 890

Text #11

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1387504 (Python Code)

Max Activating Token Index: 327

Text #12

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1634703 (Python Code)

Max Activating Token Index: 51

Text #13

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1547912 (Python Code)

Max Activating Token Index: 696

Text #14

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1641334 (Python Code)

Max Activating Token Index: 112

Text #15

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1529569 (Python Code)

Max Activating Token Index: 67

Text #16

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1380117 (Python Code)

Max Activating Token Index: 465

Text #17

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1381607 (Python Code)

Max Activating Token Index: 64

Text #18

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1655446 (Python Code)

Max Activating Token Index: 56

Text #19

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0116. Min Act: -0.0006

Data Index: 1649068 (Python Code)

Max Activating Token Index: 1018