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

Dataset: The Pile

Neuron 2957 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1465085 (The Pile)

Max Activating Token Index: 183

Text #1

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1714978 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4976. Min Act: 0.0000

Data Index: 882852 (The Pile)

Max Activating Token Index: 902

Text #3

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4601. Min Act: -0.0000

Data Index: 830200 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1254973 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1964051 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4383. Min Act: -0.0000

Data Index: 255814 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1242257 (The Pile)

Max Activating Token Index: 413

Text #8

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1799748 (The Pile)

Max Activating Token Index: 876

Text #9

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1515120 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3797. Min Act: -0.0000

Data Index: 160277 (The Pile)

Max Activating Token Index: 625

Text #11

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4057. Min Act: -0.0000

Data Index: 356633 (The Pile)

Max Activating Token Index: 479

Text #12

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3788. Min Act: -0.0000

Data Index: 681104 (The Pile)

Max Activating Token Index: 314

Text #13

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3802. Min Act: -0.0000

Data Index: 289144 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3779. Min Act: -0.0000

Data Index: 955522 (The Pile)

Max Activating Token Index: 153

Text #15

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3764. Min Act: -0.0000

Data Index: 853183 (The Pile)

Max Activating Token Index: 29

Text #16

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3874. Min Act: -0.0000

Data Index: 1708051 (The Pile)

Max Activating Token Index: 121

Text #17

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1194941 (The Pile)

Max Activating Token Index: 887

Text #18

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1689687 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1175113 (The Pile)

Max Activating Token Index: 995