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

Dataset: The Pile

Neuron 3956 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.3920. Min Act: -0.0000

Data Index: 1043541 (The Pile)

Max Activating Token Index: 394

Text #1

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.2975. Min Act: -0.0000

Data Index: 761986 (The Pile)

Max Activating Token Index: 123

Text #2

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.3582. Min Act: -0.0000

Data Index: 1674088 (The Pile)

Max Activating Token Index: 31

Text #3

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.1721. Min Act: -0.0000

Data Index: 1012578 (The Pile)

Max Activating Token Index: 71

Text #4

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.2055. Min Act: -0.0000

Data Index: 995305 (The Pile)

Max Activating Token Index: 626

Text #5

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.1157. Min Act: -0.0000

Data Index: 340561 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.0859. Min Act: -0.0000

Data Index: 1122277 (The Pile)

Max Activating Token Index: 259

Text #7

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.1290. Min Act: -0.0000

Data Index: 1457494 (The Pile)

Max Activating Token Index: 747

Text #8

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.1403. Min Act: -0.0000

Data Index: 1114927 (The Pile)

Max Activating Token Index: 371

Text #9

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.2706. Min Act: -0.0000

Data Index: 834700 (The Pile)

Max Activating Token Index: 184

Text #10

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.0800. Min Act: -0.0000

Data Index: 502422 (The Pile)

Max Activating Token Index: 54

Text #11

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.0772. Min Act: -0.0000

Data Index: 466929 (The Pile)

Max Activating Token Index: 20

Text #12

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.0444. Min Act: -0.0000

Data Index: 516205 (The Pile)

Max Activating Token Index: 898

Text #13

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.0856. Min Act: -0.0000

Data Index: 1715058 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.0435. Min Act: -0.0000

Data Index: 1398083 (The Pile)

Max Activating Token Index: 727

Text #15

Max Range: 1.3920. Min Range: -1.3920

Max Act: 0.9160. Min Act: -0.0000

Data Index: 354750 (The Pile)

Max Activating Token Index: 509

Text #16

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.0131. Min Act: -0.0000

Data Index: 1172989 (The Pile)

Max Activating Token Index: 882

Text #17

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.0503. Min Act: -0.0000

Data Index: 519648 (The Pile)

Max Activating Token Index: 656

Text #18

Max Range: 1.3920. Min Range: -1.3920

Max Act: 0.9942. Min Act: -0.0000

Data Index: 60885 (The Pile)

Max Activating Token Index: 995

Text #19

Max Range: 1.3920. Min Range: -1.3920

Max Act: 0.9766. Min Act: -0.0000

Data Index: 1533297 (The Pile)

Max Activating Token Index: 433