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

Dataset: The Pile

Neuron 1347 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1574071 (The Pile)

Max Activating Token Index: 95

Text #1

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.2407. Min Act: -0.0000

Data Index: 359989 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.1620. Min Act: -0.0000

Data Index: 2702 (The Pile)

Max Activating Token Index: 21

Text #3

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.2021. Min Act: -0.0000

Data Index: 261072 (The Pile)

Max Activating Token Index: 941

Text #4

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.2688. Min Act: -0.0000

Data Index: 221401 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0774. Min Act: -0.0000

Data Index: 85302 (The Pile)

Max Activating Token Index: 192

Text #6

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.1423. Min Act: -0.0000

Data Index: 1324369 (The Pile)

Max Activating Token Index: 393

Text #7

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.1282. Min Act: -0.0000

Data Index: 587907 (The Pile)

Max Activating Token Index: 690

Text #8

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.1143. Min Act: -0.0000

Data Index: 244282 (The Pile)

Max Activating Token Index: 952

Text #9

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9870. Min Act: -0.0000

Data Index: 823015 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.1245. Min Act: -0.0000

Data Index: 692603 (The Pile)

Max Activating Token Index: 870

Text #11

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.1027. Min Act: -0.0000

Data Index: 1801196 (The Pile)

Max Activating Token Index: 851

Text #12

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0701. Min Act: -0.0000

Data Index: 172988 (The Pile)

Max Activating Token Index: 997

Text #13

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0680. Min Act: -0.0000

Data Index: 697275 (The Pile)

Max Activating Token Index: 335

Text #14

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0901. Min Act: -0.0000

Data Index: 841694 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0735. Min Act: -0.0000

Data Index: 333850 (The Pile)

Max Activating Token Index: 214

Text #16

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0392. Min Act: -0.0000

Data Index: 1396948 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0594. Min Act: -0.0000

Data Index: 1233457 (The Pile)

Max Activating Token Index: 467

Text #18

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9795. Min Act: -0.0000

Data Index: 1613323 (The Pile)

Max Activating Token Index: 896

Text #19

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9995. Min Act: -0.0000

Data Index: 1078511 (The Pile)

Max Activating Token Index: 1000