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

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

Neuron 1814 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.4736. Min Act: -0.0001

Data Index: 1574795 (Python Code)

Max Activating Token Index: 251

Text #1

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3076. Min Act: -0.0001

Data Index: 1581279 (Python Code)

Max Activating Token Index: 630

Text #2

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.2997. Min Act: -0.0001

Data Index: 1596898 (Python Code)

Max Activating Token Index: 74

Text #3

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3297. Min Act: -0.0001

Data Index: 1570686 (Python Code)

Max Activating Token Index: 773

Text #4

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3132. Min Act: -0.0001

Data Index: 1437000 (Python Code)

Max Activating Token Index: 993

Text #5

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3047. Min Act: -0.0001

Data Index: 1587926 (Python Code)

Max Activating Token Index: 579

Text #6

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3100. Min Act: -0.0001

Data Index: 1402033 (Python Code)

Max Activating Token Index: 807

Text #7

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.2928. Min Act: -0.0001

Data Index: 1425618 (Python Code)

Max Activating Token Index: 366

Text #8

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.3032. Min Act: -0.0001

Data Index: 1623161 (Python Code)

Max Activating Token Index: 442

Text #9

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.2746. Min Act: -0.0001

Data Index: 1451444 (Python Code)

Max Activating Token Index: 197

Text #10

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.2629. Min Act: -0.0001

Data Index: 1646877 (Python Code)

Max Activating Token Index: 601

Text #11

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.2851. Min Act: -0.0001

Data Index: 1604664 (Python Code)

Max Activating Token Index: 961

Text #12

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.2743. Min Act: -0.0001

Data Index: 1649942 (Python Code)

Max Activating Token Index: 164

Text #13

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.2768. Min Act: -0.0001

Data Index: 1588287 (Python Code)

Max Activating Token Index: 458

Text #14

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1422219 (Python Code)

Max Activating Token Index: 655

Text #15

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.2520. Min Act: -0.0001

Data Index: 1593790 (Python Code)

Max Activating Token Index: 833

Text #16

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.2612. Min Act: -0.0001

Data Index: 1527697 (Python Code)

Max Activating Token Index: 647

Text #17

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.2555. Min Act: -0.0001

Data Index: 1420882 (Python Code)

Max Activating Token Index: 698

Text #18

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.2727. Min Act: -0.0001

Data Index: 1604550 (Python Code)

Max Activating Token Index: 163

Text #19

Max Range: 0.4736. Min Range: -0.4736

Max Act: 0.2619. Min Act: -0.0001

Data Index: 1628601 (Python Code)

Max Activating Token Index: 707