Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2051 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0922. Min Act: -0.0003

Data Index: 1552207 (Python Code)

Max Activating Token Index: 128

Text #1

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0745. Min Act: -0.0003

Data Index: 571296 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0752. Min Act: -0.0003

Data Index: 381906 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0677. Min Act: -0.0003

Data Index: 1340938 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0715. Min Act: -0.0003

Data Index: 279510 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0624. Min Act: -0.0003

Data Index: 1289925 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0562. Min Act: -0.0003

Data Index: 330000 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0568. Min Act: -0.0003

Data Index: 1011344 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0613. Min Act: -0.0003

Data Index: 1368493 (Python Code)

Max Activating Token Index: 158

Text #9

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0602. Min Act: -0.0003

Data Index: 465370 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0545. Min Act: -0.0003

Data Index: 28885 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0639. Min Act: -0.0003

Data Index: 889835 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0499. Min Act: -0.0003

Data Index: 365681 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1139002 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0559. Min Act: -0.0003

Data Index: 750843 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0483. Min Act: -0.0003

Data Index: 315343 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0588. Min Act: -0.0003

Data Index: 1199744 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0552. Min Act: -0.0003

Data Index: 321823 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0586. Min Act: -0.0003

Data Index: 902458 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1219997 (C4 (Web Text))

Max Activating Token Index: 244