Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4610 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5745. Min Act: -0.0002

Data Index: 224560 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5541. Min Act: -0.0003

Data Index: 98354 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5268. Min Act: -0.0003

Data Index: 735166 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4971. Min Act: -0.0003

Data Index: 266668 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5145. Min Act: -0.0003

Data Index: 932508 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5126. Min Act: -0.0003

Data Index: 957910 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4944. Min Act: -0.0003

Data Index: 104003 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4696. Min Act: -0.0003

Data Index: 668690 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4726. Min Act: -0.0003

Data Index: 1147618 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4706. Min Act: -0.0002

Data Index: 1256654 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4682. Min Act: -0.0003

Data Index: 1213734 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4661. Min Act: -0.0003

Data Index: 878699 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4634. Min Act: -0.0003

Data Index: 172495 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4574. Min Act: -0.0003

Data Index: 106762 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4571. Min Act: -0.0003

Data Index: 16279 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4724. Min Act: -0.0003

Data Index: 850897 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4452. Min Act: -0.0003

Data Index: 667205 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4558. Min Act: -0.0003

Data Index: 593211 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4537. Min Act: -0.0003

Data Index: 570791 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4622. Min Act: -0.0002

Data Index: 573861 (C4 (Web Text))

Max Activating Token Index: 962