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

Dataset: The Pile

Neuron 2162 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1224968 (The Pile)

Max Activating Token Index: 134

Text #1

Max Range: 1.0650. Min Range: -1.0650

Max Act: 1.0387. Min Act: -0.0000

Data Index: 1225511 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 1.0650. Min Range: -1.0650

Max Act: 1.0650. Min Act: -0.0000

Data Index: 339439 (The Pile)

Max Activating Token Index: 168

Text #3

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1482731 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8896. Min Act: -0.0000

Data Index: 427446 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9718. Min Act: -0.0000

Data Index: 268943 (The Pile)

Max Activating Token Index: 92

Text #6

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9606. Min Act: -0.0000

Data Index: 713991 (The Pile)

Max Activating Token Index: 733

Text #7

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9414. Min Act: -0.0000

Data Index: 764065 (The Pile)

Max Activating Token Index: 690

Text #8

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9583. Min Act: -0.0000

Data Index: 1795453 (The Pile)

Max Activating Token Index: 445

Text #9

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9627. Min Act: -0.0000

Data Index: 1448243 (The Pile)

Max Activating Token Index: 608

Text #10

Max Range: 1.0650. Min Range: -1.0650

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1977537 (The Pile)

Max Activating Token Index: 727

Text #11

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9700. Min Act: -0.0000

Data Index: 428332 (The Pile)

Max Activating Token Index: 397

Text #12

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1637733 (The Pile)

Max Activating Token Index: 457

Text #13

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9002. Min Act: -0.0000

Data Index: 304959 (The Pile)

Max Activating Token Index: 596

Text #14

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9251. Min Act: -0.0000

Data Index: 1245036 (The Pile)

Max Activating Token Index: 750

Text #15

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9246. Min Act: -0.0000

Data Index: 1392776 (The Pile)

Max Activating Token Index: 397

Text #16

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9043. Min Act: -0.0000

Data Index: 118330 (The Pile)

Max Activating Token Index: 174

Text #17

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9170. Min Act: -0.0000

Data Index: 227783 (The Pile)

Max Activating Token Index: 406

Text #18

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1170810 (The Pile)

Max Activating Token Index: 268

Text #19

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9958. Min Act: -0.0000

Data Index: 1933129 (The Pile)

Max Activating Token Index: 745