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

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

Neuron 2400 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: 0.0138. Min Act: -0.0004

Data Index: 489678 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0111. Min Act: -0.0004

Data Index: 1004089 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0123. Min Act: -0.0004

Data Index: 854330 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0121. Min Act: -0.0004

Data Index: 1371314 (Python Code)

Max Activating Token Index: 129

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0117. Min Act: -0.0004

Data Index: 1487007 (Python Code)

Max Activating Token Index: 479

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0121. Min Act: -0.0004

Data Index: 1430000 (Python Code)

Max Activating Token Index: 443

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0112. Min Act: -0.0004

Data Index: 1430069 (Python Code)

Max Activating Token Index: 503

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0112. Min Act: -0.0004

Data Index: 1533727 (Python Code)

Max Activating Token Index: 447

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0115. Min Act: -0.0004

Data Index: 1527361 (Python Code)

Max Activating Token Index: 471

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0112. Min Act: -0.0004

Data Index: 1636534 (Python Code)

Max Activating Token Index: 215

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0113. Min Act: -0.0004

Data Index: 1390869 (Python Code)

Max Activating Token Index: 503

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0125. Min Act: -0.0004

Data Index: 1608600 (Python Code)

Max Activating Token Index: 964

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0118. Min Act: -0.0004

Data Index: 1251386 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0103. Min Act: -0.0004

Data Index: 1360661 (Python Code)

Max Activating Token Index: 600

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0112. Min Act: -0.0004

Data Index: 1477411 (Python Code)

Max Activating Token Index: 273

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0109. Min Act: -0.0004

Data Index: 1447678 (Python Code)

Max Activating Token Index: 417

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0116. Min Act: -0.0004

Data Index: 397256 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0108. Min Act: -0.0004

Data Index: 1398746 (Python Code)

Max Activating Token Index: 526

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0105. Min Act: -0.0004

Data Index: 293128 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0104. Min Act: -0.0004

Data Index: 1608755 (Python Code)

Max Activating Token Index: 984