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

Dataset: The Pile

Neuron 1420 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.5050. Min Act: -0.0000

Data Index: 283602 (The Pile)

Max Activating Token Index: 899

Text #1

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.3958. Min Act: -0.0000

Data Index: 481586 (The Pile)

Max Activating Token Index: 334

Text #2

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.2519. Min Act: -0.0000

Data Index: 832380 (The Pile)

Max Activating Token Index: 980

Text #3

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1461511 (The Pile)

Max Activating Token Index: 1014

Text #4

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.1821. Min Act: -0.0000

Data Index: 468909 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.1089. Min Act: -0.0000

Data Index: 229690 (The Pile)

Max Activating Token Index: 284

Text #6

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.1359. Min Act: -0.0000

Data Index: 931507 (The Pile)

Max Activating Token Index: 46

Text #7

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.0564. Min Act: -0.0000

Data Index: 885832 (The Pile)

Max Activating Token Index: 321

Text #8

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.1410. Min Act: -0.0000

Data Index: 370558 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.1045. Min Act: -0.0000

Data Index: 1186422 (The Pile)

Max Activating Token Index: 304

Text #10

Max Range: 1.5050. Min Range: -1.5050

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1605347 (The Pile)

Max Activating Token Index: 978

Text #11

Max Range: 1.5050. Min Range: -1.5050

Max Act: 0.9335. Min Act: -0.0000

Data Index: 484879 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1383089 (The Pile)

Max Activating Token Index: 508

Text #13

Max Range: 1.5050. Min Range: -1.5050

Max Act: 0.9828. Min Act: -0.0000

Data Index: 253132 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.0083. Min Act: -0.0000

Data Index: 461207 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.0042. Min Act: -0.0000

Data Index: 1134267 (The Pile)

Max Activating Token Index: 672

Text #16

Max Range: 1.5050. Min Range: -1.5050

Max Act: 0.9641. Min Act: -0.0000

Data Index: 864963 (The Pile)

Max Activating Token Index: 1008

Text #17

Max Range: 1.5050. Min Range: -1.5050

Max Act: 0.9713. Min Act: -0.0000

Data Index: 1366541 (The Pile)

Max Activating Token Index: 715

Text #18

Max Range: 1.5050. Min Range: -1.5050

Max Act: 1.0332. Min Act: -0.0000

Data Index: 83231 (The Pile)

Max Activating Token Index: 769

Text #19

Max Range: 1.5050. Min Range: -1.5050

Max Act: 0.9871. Min Act: -0.0000

Data Index: 1348922 (The Pile)

Max Activating Token Index: 633