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

Dataset: The Pile

Neuron 1986 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.3589. Min Act: -0.0000

Data Index: 772361 (The Pile)

Max Activating Token Index: 926

Text #1

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.3967. Min Act: -0.0000

Data Index: 1719737 (The Pile)

Max Activating Token Index: 912

Text #2

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.2039. Min Act: -0.0000

Data Index: 610616 (The Pile)

Max Activating Token Index: 468

Text #3

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.2142. Min Act: -0.0000

Data Index: 1824826 (The Pile)

Max Activating Token Index: 463

Text #4

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0417. Min Act: -0.0000

Data Index: 597052 (The Pile)

Max Activating Token Index: 502

Text #5

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0832. Min Act: -0.0000

Data Index: 1099169 (The Pile)

Max Activating Token Index: 837

Text #6

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.9592. Min Act: -0.0000

Data Index: 461855 (The Pile)

Max Activating Token Index: 321

Text #7

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.9931. Min Act: -0.0000

Data Index: 851646 (The Pile)

Max Activating Token Index: 693

Text #8

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.1512. Min Act: -0.0000

Data Index: 1089352 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0677. Min Act: -0.0000

Data Index: 412255 (The Pile)

Max Activating Token Index: 400

Text #10

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1437239 (The Pile)

Max Activating Token Index: 304

Text #11

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0018. Min Act: -0.0000

Data Index: 1742558 (The Pile)

Max Activating Token Index: 936

Text #12

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0760. Min Act: -0.0000

Data Index: 338063 (The Pile)

Max Activating Token Index: 620

Text #13

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0605. Min Act: -0.0000

Data Index: 1396538 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0609. Min Act: -0.0000

Data Index: 627282 (The Pile)

Max Activating Token Index: 20

Text #15

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1067410 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0187. Min Act: -0.0000

Data Index: 1732239 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0428. Min Act: -0.0000

Data Index: 291790 (The Pile)

Max Activating Token Index: 1008

Text #18

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1047439 (The Pile)

Max Activating Token Index: 494

Text #19

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0082. Min Act: -0.0000

Data Index: 1158161 (The Pile)

Max Activating Token Index: 294