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

Dataset: The Pile

Neuron 1684 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: 1.1884. Min Range: -1.1884

Max Act: 1.1874. Min Act: -0.0000

Data Index: 1554850 (The Pile)

Max Activating Token Index: 1002

Text #1

Max Range: 1.1884. Min Range: -1.1884

Max Act: 1.1884. Min Act: -0.0000

Data Index: 841910 (The Pile)

Max Activating Token Index: 1013

Text #2

Max Range: 1.1884. Min Range: -1.1884

Max Act: 1.0899. Min Act: -0.0000

Data Index: 1187767 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 1.1884. Min Range: -1.1884

Max Act: 1.0761. Min Act: -0.0000

Data Index: 589061 (The Pile)

Max Activating Token Index: 725

Text #4

Max Range: 1.1884. Min Range: -1.1884

Max Act: 1.0076. Min Act: -0.0000

Data Index: 627033 (The Pile)

Max Activating Token Index: 652

Text #5

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9686. Min Act: -0.0000

Data Index: 986845 (The Pile)

Max Activating Token Index: 703

Text #6

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9055. Min Act: -0.0000

Data Index: 338496 (The Pile)

Max Activating Token Index: 776

Text #7

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.8973. Min Act: -0.0000

Data Index: 536914 (The Pile)

Max Activating Token Index: 465

Text #8

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9464. Min Act: -0.0000

Data Index: 192316 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.8838. Min Act: -0.0000

Data Index: 427428 (The Pile)

Max Activating Token Index: 263

Text #10

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9972. Min Act: -0.0000

Data Index: 463319 (The Pile)

Max Activating Token Index: 363

Text #11

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1388481 (The Pile)

Max Activating Token Index: 241

Text #12

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9327. Min Act: -0.0000

Data Index: 767414 (The Pile)

Max Activating Token Index: 239

Text #13

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.8609. Min Act: -0.0000

Data Index: 1868452 (The Pile)

Max Activating Token Index: 384

Text #14

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9170. Min Act: -0.0000

Data Index: 1514207 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.8560. Min Act: -0.0000

Data Index: 788313 (The Pile)

Max Activating Token Index: 544

Text #16

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1715024 (The Pile)

Max Activating Token Index: 857

Text #17

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.8971. Min Act: -0.0000

Data Index: 586677 (The Pile)

Max Activating Token Index: 335

Text #18

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.8888. Min Act: -0.0000

Data Index: 764848 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9132. Min Act: -0.0000

Data Index: 1552593 (The Pile)

Max Activating Token Index: 289