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

Dataset: The Pile

Neuron 81 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: 1.9630. Min Range: -1.9630

Max Act: 1.9630. Min Act: -0.0000

Data Index: 1134222 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.8696. Min Act: -0.0000

Data Index: 1594984 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.9570. Min Act: -0.0000

Data Index: 505552 (The Pile)

Max Activating Token Index: 605

Text #3

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.5608. Min Act: -0.0000

Data Index: 366455 (The Pile)

Max Activating Token Index: 32

Text #4

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.8042. Min Act: -0.0000

Data Index: 977144 (The Pile)

Max Activating Token Index: 273

Text #5

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.7321. Min Act: -0.0000

Data Index: 1212607 (The Pile)

Max Activating Token Index: 1010

Text #6

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.8915. Min Act: -0.0000

Data Index: 328475 (The Pile)

Max Activating Token Index: 705

Text #7

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.7660. Min Act: -0.0000

Data Index: 1159403 (The Pile)

Max Activating Token Index: 998

Text #8

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.8835. Min Act: -0.0000

Data Index: 1559257 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.4913. Min Act: -0.0000

Data Index: 1934632 (The Pile)

Max Activating Token Index: 835

Text #10

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.9408. Min Act: -0.0000

Data Index: 1582754 (The Pile)

Max Activating Token Index: 518

Text #11

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.6389. Min Act: -0.0000

Data Index: 1035490 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.6913. Min Act: -0.0000

Data Index: 770835 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.6914. Min Act: -0.0000

Data Index: 119418 (The Pile)

Max Activating Token Index: 103

Text #14

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.6197. Min Act: -0.0000

Data Index: 1863658 (The Pile)

Max Activating Token Index: 650

Text #15

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.6964. Min Act: -0.0000

Data Index: 1076067 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.6870. Min Act: -0.0000

Data Index: 21915 (The Pile)

Max Activating Token Index: 420

Text #17

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.6648. Min Act: -0.0000

Data Index: 850464 (The Pile)

Max Activating Token Index: 350

Text #18

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.5578. Min Act: -0.0000

Data Index: 974256 (The Pile)

Max Activating Token Index: 518

Text #19

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.6666. Min Act: -0.0000

Data Index: 1506210 (The Pile)

Max Activating Token Index: 479