Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2399 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1490710 (Python Code)

Max Activating Token Index: 600

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1414991 (Python Code)

Max Activating Token Index: 196

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 301601 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1481526 (Python Code)

Max Activating Token Index: 602

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1580957 (Python Code)

Max Activating Token Index: 633

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1564017 (Python Code)

Max Activating Token Index: 874

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1488143 (Python Code)

Max Activating Token Index: 263

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1623281 (Python Code)

Max Activating Token Index: 734

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1295336 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1579512 (Python Code)

Max Activating Token Index: 835

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1093172 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1104039 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1249445 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1175328 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1598398 (Python Code)

Max Activating Token Index: 739

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1321711 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0053. Min Act: -0.0003

Data Index: 885244 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1622018 (Python Code)

Max Activating Token Index: 305

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0051. Min Act: -0.0002

Data Index: 1423371 (Python Code)

Max Activating Token Index: 237

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1498475 (Python Code)

Max Activating Token Index: 769