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

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

Neuron 654 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: 0.0573. Min Range: -0.0573

Max Act: 0.0573. Min Act: -0.0002

Data Index: 544607 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1420300 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0532. Min Act: -0.0002

Data Index: 379327 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0536. Min Act: -0.0002

Data Index: 831827 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0513. Min Act: -0.0002

Data Index: 398365 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0526. Min Act: -0.0002

Data Index: 871181 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0520. Min Act: -0.0002

Data Index: 332272 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0514. Min Act: -0.0002

Data Index: 829139 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0510. Min Act: -0.0002

Data Index: 521494 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0509. Min Act: -0.0002

Data Index: 407391 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0509. Min Act: -0.0002

Data Index: 715185 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0509. Min Act: -0.0002

Data Index: 440753 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0495. Min Act: -0.0002

Data Index: 206708 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1656865 (Python Code)

Max Activating Token Index: 278

Text #14

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0494. Min Act: -0.0002

Data Index: 439406 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0512. Min Act: -0.0002

Data Index: 103486 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1235201 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0482. Min Act: -0.0002

Data Index: 526715 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0480. Min Act: -0.0002

Data Index: 162431 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0500. Min Act: -0.0002

Data Index: 210122 (C4 (Web Text))

Max Activating Token Index: 932