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

Dataset: The Pile

Neuron 2703 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: 0.1235. Min Range: -0.1235

Max Act: 0.1235. Min Act: -0.0000

Data Index: 1143699 (The Pile)

Max Activating Token Index: 334

Text #1

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1128. Min Act: -0.0000

Data Index: 511622 (The Pile)

Max Activating Token Index: 327

Text #2

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1068. Min Act: -0.0000

Data Index: 684917 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1351773 (The Pile)

Max Activating Token Index: 608

Text #4

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1005. Min Act: -0.0000

Data Index: 815488 (The Pile)

Max Activating Token Index: 326

Text #5

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1465514 (The Pile)

Max Activating Token Index: 266

Text #6

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1684867 (The Pile)

Max Activating Token Index: 831

Text #7

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0939. Min Act: -0.0000

Data Index: 209521 (The Pile)

Max Activating Token Index: 802

Text #8

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1902747 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0914. Min Act: -0.0000

Data Index: 1036746 (The Pile)

Max Activating Token Index: 611

Text #10

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0911. Min Act: -0.0000

Data Index: 420458 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0942. Min Act: -0.0000

Data Index: 41341 (The Pile)

Max Activating Token Index: 441

Text #12

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0906. Min Act: -0.0000

Data Index: 831573 (The Pile)

Max Activating Token Index: 17

Text #13

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0866. Min Act: -0.0000

Data Index: 375480 (The Pile)

Max Activating Token Index: 407

Text #14

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1698544 (The Pile)

Max Activating Token Index: 667

Text #15

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0790. Min Act: -0.0000

Data Index: 867828 (The Pile)

Max Activating Token Index: 775

Text #16

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0890. Min Act: -0.0000

Data Index: 956844 (The Pile)

Max Activating Token Index: 220

Text #17

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1264442 (The Pile)

Max Activating Token Index: 608

Text #18

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0751. Min Act: -0.0000

Data Index: 245345 (The Pile)

Max Activating Token Index: 641

Text #19

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1333776 (The Pile)

Max Activating Token Index: 945