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

Dataset: The Pile

Neuron 1555 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.4970. Min Act: -0.0000

Data Index: 1963551 (The Pile)

Max Activating Token Index: 534

Text #1

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.2996. Min Act: -0.0000

Data Index: 782899 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.3156. Min Act: -0.0000

Data Index: 229968 (The Pile)

Max Activating Token Index: 211

Text #3

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.2981. Min Act: 0.0000

Data Index: 450031 (The Pile)

Max Activating Token Index: 414

Text #4

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.3657. Min Act: -0.0000

Data Index: 1785563 (The Pile)

Max Activating Token Index: 178

Text #5

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0632. Min Act: -0.0000

Data Index: 436554 (The Pile)

Max Activating Token Index: 249

Text #6

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.3271. Min Act: -0.0000

Data Index: 340138 (The Pile)

Max Activating Token Index: 283

Text #7

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.1896. Min Act: -0.0000

Data Index: 828788 (The Pile)

Max Activating Token Index: 26

Text #8

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0712. Min Act: -0.0000

Data Index: 1042456 (The Pile)

Max Activating Token Index: 15

Text #9

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0465. Min Act: -0.0000

Data Index: 1200904 (The Pile)

Max Activating Token Index: 616

Text #10

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0775. Min Act: -0.0000

Data Index: 1524027 (The Pile)

Max Activating Token Index: 178

Text #11

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0080. Min Act: -0.0000

Data Index: 44683 (The Pile)

Max Activating Token Index: 563

Text #12

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0654. Min Act: -0.0000

Data Index: 665122 (The Pile)

Max Activating Token Index: 309

Text #13

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0412. Min Act: -0.0000

Data Index: 1756875 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1090057 (The Pile)

Max Activating Token Index: 906

Text #15

Max Range: 1.4970. Min Range: -1.4970

Max Act: 0.9614. Min Act: -0.0000

Data Index: 899140 (The Pile)

Max Activating Token Index: 317

Text #16

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1060536 (The Pile)

Max Activating Token Index: 404

Text #17

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0065. Min Act: -0.0000

Data Index: 867078 (The Pile)

Max Activating Token Index: 257

Text #18

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0091. Min Act: -0.0000

Data Index: 1639376 (The Pile)

Max Activating Token Index: 901

Text #19

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0057. Min Act: -0.0000

Data Index: 969729 (The Pile)

Max Activating Token Index: 791