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

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

Neuron 3807 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.4619. Min Act: -0.0000

Data Index: 1362103 (Python Code)

Max Activating Token Index: 624

Text #1

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1575641 (Python Code)

Max Activating Token Index: 604

Text #2

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.4003. Min Act: -0.0000

Data Index: 1573751 (Python Code)

Max Activating Token Index: 866

Text #3

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1368571 (Python Code)

Max Activating Token Index: 684

Text #4

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1470127 (Python Code)

Max Activating Token Index: 916

Text #5

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3912. Min Act: -0.0000

Data Index: 1415118 (Python Code)

Max Activating Token Index: 822

Text #6

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1427620 (Python Code)

Max Activating Token Index: 628

Text #7

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3889. Min Act: -0.0000

Data Index: 1535935 (Python Code)

Max Activating Token Index: 540

Text #8

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1393796 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1449073 (Python Code)

Max Activating Token Index: 456

Text #10

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1545614 (Python Code)

Max Activating Token Index: 370

Text #11

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1591734 (Python Code)

Max Activating Token Index: 26

Text #12

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1591009 (Python Code)

Max Activating Token Index: 568

Text #13

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1601011 (Python Code)

Max Activating Token Index: 688

Text #14

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1594345 (Python Code)

Max Activating Token Index: 1006

Text #15

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1457552 (Python Code)

Max Activating Token Index: 415

Text #16

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.4003. Min Act: -0.0000

Data Index: 1620439 (Python Code)

Max Activating Token Index: 1010

Text #17

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1536598 (Python Code)

Max Activating Token Index: 62

Text #18

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1415450 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 0.4619. Min Range: -0.4619

Max Act: 0.3758. Min Act: -0.0000

Data Index: 1400843 (Python Code)

Max Activating Token Index: 211