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

Dataset: The Pile

Neuron 13 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: 0.8004. Min Range: -0.8004

Max Act: 0.8004. Min Act: -0.0000

Data Index: 222387 (The Pile)

Max Activating Token Index: 552

Text #1

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.6381. Min Act: -0.0000

Data Index: 507925 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5694. Min Act: -0.0000

Data Index: 1475932 (The Pile)

Max Activating Token Index: 768

Text #3

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1587992 (The Pile)

Max Activating Token Index: 720

Text #4

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1338083 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5225. Min Act: -0.0000

Data Index: 935354 (The Pile)

Max Activating Token Index: 871

Text #6

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5605. Min Act: -0.0000

Data Index: 890450 (The Pile)

Max Activating Token Index: 921

Text #7

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1931845 (The Pile)

Max Activating Token Index: 879

Text #8

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.4936. Min Act: -0.0000

Data Index: 288927 (The Pile)

Max Activating Token Index: 634

Text #9

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1119453 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.4813. Min Act: -0.0000

Data Index: 419411 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.4911. Min Act: -0.0000

Data Index: 159224 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1132113 (The Pile)

Max Activating Token Index: 496

Text #13

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1435905 (The Pile)

Max Activating Token Index: 683

Text #14

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.4682. Min Act: -0.0000

Data Index: 252076 (The Pile)

Max Activating Token Index: 470

Text #15

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.4410. Min Act: -0.0000

Data Index: 137367 (The Pile)

Max Activating Token Index: 489

Text #16

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1146590 (The Pile)

Max Activating Token Index: 492

Text #17

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1759123 (The Pile)

Max Activating Token Index: 99

Text #18

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1172173 (The Pile)

Max Activating Token Index: 139

Text #19

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1407908 (The Pile)

Max Activating Token Index: 251