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

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

Neuron 3651 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0002

Data Index: 972472 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0002

Data Index: 557665 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0002

Data Index: 533553 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0002

Data Index: 126794 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1141638 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 513717 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 282775 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1303546 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 74024 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0003

Data Index: 407245 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 906849 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 305913 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1444520 (Python Code)

Max Activating Token Index: 704

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1301140 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0003

Data Index: 790270 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0003

Data Index: 738088 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0003

Data Index: 253041 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1337373 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0003

Data Index: 476295 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1305802 (C4 (Web Text))

Max Activating Token Index: 250