Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1356 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0082. Min Act: -0.0004

Data Index: 1453427 (Python Code)

Max Activating Token Index: 737

Text #1

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0083. Min Act: -0.0004

Data Index: 221702 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0081. Min Act: -0.0004

Data Index: 296965 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0080. Min Act: -0.0004

Data Index: 1610237 (Python Code)

Max Activating Token Index: 240

Text #4

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0079. Min Act: -0.0004

Data Index: 165209 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0079. Min Act: -0.0004

Data Index: 1430675 (Python Code)

Max Activating Token Index: 107

Text #6

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0079. Min Act: -0.0004

Data Index: 1425768 (Python Code)

Max Activating Token Index: 731

Text #7

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0004

Data Index: 276701 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0004

Data Index: 830798 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0004

Data Index: 1418337 (Python Code)

Max Activating Token Index: 961

Text #10

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0004

Data Index: 1601311 (Python Code)

Max Activating Token Index: 781

Text #11

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0004

Data Index: 1390038 (Python Code)

Max Activating Token Index: 124

Text #12

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0004

Data Index: 224443 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0004

Data Index: 1459924 (Python Code)

Max Activating Token Index: 473

Text #14

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0004

Data Index: 591466 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0004

Data Index: 208597 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0004

Data Index: 1637574 (Python Code)

Max Activating Token Index: 954

Text #17

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0004

Data Index: 1631068 (Python Code)

Max Activating Token Index: 264

Text #18

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0004

Data Index: 1062536 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0004

Data Index: 1399617 (Python Code)

Max Activating Token Index: 237