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

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

Neuron 707 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: 0.0760. Min Range: -0.0760

Max Act: 0.0760. Min Act: -0.0002

Data Index: 618382 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0680. Min Act: -0.0002

Data Index: 983321 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0622. Min Act: -0.0002

Data Index: 779278 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0621. Min Act: -0.0002

Data Index: 135083 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0627. Min Act: -0.0002

Data Index: 1068923 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0573. Min Act: -0.0002

Data Index: 555758 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0555. Min Act: -0.0002

Data Index: 737355 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0542. Min Act: -0.0001

Data Index: 650664 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1011677 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0530. Min Act: -0.0002

Data Index: 528046 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0516. Min Act: -0.0001

Data Index: 833497 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1063525 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0501. Min Act: -0.0002

Data Index: 961576 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0475. Min Act: -0.0002

Data Index: 241026 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0535. Min Act: -0.0002

Data Index: 594264 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0493. Min Act: -0.0002

Data Index: 991781 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0474. Min Act: -0.0001

Data Index: 977730 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1057683 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1309608 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0451. Min Act: -0.0001

Data Index: 457582 (C4 (Web Text))

Max Activating Token Index: 673