Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 336 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0121. Min Act: -0.0004

Data Index: 1517534 (Python Code)

Max Activating Token Index: 355

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0004

Data Index: 1562426 (Python Code)

Max Activating Token Index: 357

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0105. Min Act: -0.0004

Data Index: 1596568 (Python Code)

Max Activating Token Index: 551

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0125. Min Act: -0.0004

Data Index: 1523523 (Python Code)

Max Activating Token Index: 875

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0115. Min Act: -0.0004

Data Index: 1581991 (Python Code)

Max Activating Token Index: 422

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0125. Min Act: -0.0004

Data Index: 1456878 (Python Code)

Max Activating Token Index: 646

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0132. Min Act: -0.0004

Data Index: 1474382 (Python Code)

Max Activating Token Index: 887

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0118. Min Act: -0.0004

Data Index: 1609843 (Python Code)

Max Activating Token Index: 1004

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0126. Min Act: -0.0004

Data Index: 1502912 (Python Code)

Max Activating Token Index: 984

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0122. Min Act: -0.0004

Data Index: 1423906 (Python Code)

Max Activating Token Index: 811

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0137. Min Act: -0.0004

Data Index: 1383822 (Python Code)

Max Activating Token Index: 587

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0101. Min Act: -0.0004

Data Index: 1649853 (Python Code)

Max Activating Token Index: 550

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0118. Min Act: -0.0004

Data Index: 1493816 (Python Code)

Max Activating Token Index: 986

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0135. Min Act: -0.0004

Data Index: 1361220 (Python Code)

Max Activating Token Index: 590

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0120. Min Act: -0.0004

Data Index: 1506535 (Python Code)

Max Activating Token Index: 138

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0121. Min Act: -0.0004

Data Index: 1503295 (Python Code)

Max Activating Token Index: 531

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0120. Min Act: -0.0004

Data Index: 1559967 (Python Code)

Max Activating Token Index: 884

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0134. Min Act: -0.0004

Data Index: 1523709 (Python Code)

Max Activating Token Index: 616

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0111. Min Act: -0.0004

Data Index: 1374694 (Python Code)

Max Activating Token Index: 259

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0116. Min Act: -0.0004

Data Index: 1537630 (Python Code)

Max Activating Token Index: 183