Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 377 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0003

Data Index: 168456 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0004

Data Index: 384843 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0080. Min Act: -0.0004

Data Index: 309659 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1557471 (Python Code)

Max Activating Token Index: 698

Text #4

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0004

Data Index: 676870 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0003

Data Index: 694751 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1495302 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0080. Min Act: -0.0003

Data Index: 1466523 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0074. Min Act: -0.0003

Data Index: 218915 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1447642 (Python Code)

Max Activating Token Index: 188

Text #10

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0074. Min Act: -0.0003

Data Index: 329625 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1450935 (Python Code)

Max Activating Token Index: 631

Text #12

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0074. Min Act: -0.0003

Data Index: 1402244 (Python Code)

Max Activating Token Index: 722

Text #13

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1011812 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0069. Min Act: -0.0003

Data Index: 5006 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1265959 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0071. Min Act: -0.0003

Data Index: 807389 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1082545 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0071. Min Act: -0.0003

Data Index: 281162 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0067. Min Act: -0.0003

Data Index: 959507 (C4 (Web Text))

Max Activating Token Index: 551