Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1564 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0795. Min Act: -0.0002

Data Index: 168384 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0727. Min Act: -0.0002

Data Index: 233411 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0697. Min Act: -0.0002

Data Index: 954442 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1447438 (Python Code)

Max Activating Token Index: 335

Text #4

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0641. Min Act: -0.0002

Data Index: 951006 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1460427 (Python Code)

Max Activating Token Index: 268

Text #6

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0625. Min Act: -0.0002

Data Index: 161540 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0621. Min Act: -0.0002

Data Index: 956538 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0635. Min Act: -0.0002

Data Index: 137643 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0599. Min Act: -0.0002

Data Index: 489952 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1398388 (Python Code)

Max Activating Token Index: 248

Text #11

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0625. Min Act: -0.0002

Data Index: 421969 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0604. Min Act: -0.0002

Data Index: 427985 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0616. Min Act: -0.0002

Data Index: 646341 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0632. Min Act: -0.0002

Data Index: 809058 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1511032 (Python Code)

Max Activating Token Index: 412

Text #16

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1543027 (Python Code)

Max Activating Token Index: 908

Text #17

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0610. Min Act: -0.0002

Data Index: 561583 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0616. Min Act: -0.0002

Data Index: 157770 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1349112 (C4 (Web Text))

Max Activating Token Index: 49