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

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

Neuron 2741 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4484. Min Act: -0.0000

Data Index: 820278 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4395. Min Act: -0.0000

Data Index: 75452 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4106. Min Act: -0.0000

Data Index: 127763 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4126. Min Act: -0.0000

Data Index: 933346 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4025. Min Act: -0.0000

Data Index: 1278282 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3795. Min Act: -0.0000

Data Index: 135715 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3892. Min Act: -0.0000

Data Index: 798140 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3763. Min Act: -0.0001

Data Index: 489638 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1006438 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3962. Min Act: -0.0000

Data Index: 665708 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1358437 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3633. Min Act: -0.0000

Data Index: 566950 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3758. Min Act: -0.0000

Data Index: 737334 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3744. Min Act: -0.0000

Data Index: 906371 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3609. Min Act: -0.0000

Data Index: 827367 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3719. Min Act: -0.0000

Data Index: 963693 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3608. Min Act: -0.0000

Data Index: 181083 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3678. Min Act: -0.0001

Data Index: 611384 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3527. Min Act: -0.0000

Data Index: 710279 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3632. Min Act: -0.0000

Data Index: 663530 (C4 (Web Text))

Max Activating Token Index: 479