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

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

Neuron 1250 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1330646 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4317. Min Act: -0.0001

Data Index: 1489040 (Python Code)

Max Activating Token Index: 805

Text #2

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3920. Min Act: -0.0001

Data Index: 1384087 (Python Code)

Max Activating Token Index: 565

Text #3

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3859. Min Act: -0.0001

Data Index: 1489728 (Python Code)

Max Activating Token Index: 45

Text #4

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3965. Min Act: -0.0001

Data Index: 1370437 (Python Code)

Max Activating Token Index: 449

Text #5

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3644. Min Act: -0.0001

Data Index: 1542439 (Python Code)

Max Activating Token Index: 907

Text #6

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3663. Min Act: -0.0001

Data Index: 1459289 (Python Code)

Max Activating Token Index: 810

Text #7

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4000. Min Act: -0.0001

Data Index: 1445789 (Python Code)

Max Activating Token Index: 361

Text #8

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3726. Min Act: -0.0001

Data Index: 581599 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3785. Min Act: -0.0001

Data Index: 1501676 (Python Code)

Max Activating Token Index: 199

Text #10

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3784. Min Act: -0.0000

Data Index: 1551516 (Python Code)

Max Activating Token Index: 476

Text #11

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3652. Min Act: -0.0001

Data Index: 1546313 (Python Code)

Max Activating Token Index: 438

Text #12

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3737. Min Act: -0.0001

Data Index: 1483892 (Python Code)

Max Activating Token Index: 889

Text #13

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3704. Min Act: -0.0001

Data Index: 1553108 (Python Code)

Max Activating Token Index: 563

Text #14

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3692. Min Act: -0.0001

Data Index: 1510086 (Python Code)

Max Activating Token Index: 158

Text #15

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3689. Min Act: -0.0001

Data Index: 1502605 (Python Code)

Max Activating Token Index: 322

Text #16

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1385928 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3501. Min Act: -0.0001

Data Index: 1395852 (Python Code)

Max Activating Token Index: 864

Text #18

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1497348 (Python Code)

Max Activating Token Index: 86

Text #19

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1456849 (Python Code)

Max Activating Token Index: 777