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

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

Neuron 1097 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: 0.0129. Min Range: -0.0129

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1375944 (Python Code)

Max Activating Token Index: 310

Text #1

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1570232 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1398707 (Python Code)

Max Activating Token Index: 717

Text #3

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1578664 (Python Code)

Max Activating Token Index: 689

Text #4

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1544466 (Python Code)

Max Activating Token Index: 44

Text #5

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1456104 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1603700 (Python Code)

Max Activating Token Index: 58

Text #7

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1570505 (Python Code)

Max Activating Token Index: 815

Text #8

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0113. Min Act: -0.0006

Data Index: 1447476 (Python Code)

Max Activating Token Index: 166

Text #9

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1415728 (Python Code)

Max Activating Token Index: 564

Text #10

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0113. Min Act: -0.0006

Data Index: 1575909 (Python Code)

Max Activating Token Index: 80

Text #11

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1364373 (Python Code)

Max Activating Token Index: 315

Text #12

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1611336 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1477773 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1563777 (Python Code)

Max Activating Token Index: 58

Text #15

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1578489 (Python Code)

Max Activating Token Index: 172

Text #16

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1361232 (Python Code)

Max Activating Token Index: 518

Text #17

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1380509 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1602810 (Python Code)

Max Activating Token Index: 428

Text #19

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1474748 (Python Code)

Max Activating Token Index: 101