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

Dataset: The Pile

Neuron 2609 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.7154. Min Act: -0.0000

Data Index: 567027 (The Pile)

Max Activating Token Index: 330

Text #1

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1915655 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1330537 (The Pile)

Max Activating Token Index: 788

Text #3

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1975829 (The Pile)

Max Activating Token Index: 300

Text #4

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6538. Min Act: -0.0000

Data Index: 536695 (The Pile)

Max Activating Token Index: 649

Text #5

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1135446 (The Pile)

Max Activating Token Index: 699

Text #6

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6258. Min Act: -0.0000

Data Index: 716484 (The Pile)

Max Activating Token Index: 943

Text #7

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1706013 (The Pile)

Max Activating Token Index: 689

Text #8

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5924. Min Act: -0.0000

Data Index: 1466763 (The Pile)

Max Activating Token Index: 671

Text #9

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1335252 (The Pile)

Max Activating Token Index: 772

Text #10

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6057. Min Act: -0.0000

Data Index: 729903 (The Pile)

Max Activating Token Index: 608

Text #11

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5951. Min Act: -0.0000

Data Index: 1471076 (The Pile)

Max Activating Token Index: 699

Text #12

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6051. Min Act: -0.0000

Data Index: 217220 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5794. Min Act: -0.0000

Data Index: 467965 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6163. Min Act: -0.0000

Data Index: 936083 (The Pile)

Max Activating Token Index: 250

Text #15

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5708. Min Act: -0.0000

Data Index: 460388 (The Pile)

Max Activating Token Index: 898

Text #16

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5506. Min Act: -0.0000

Data Index: 156500 (The Pile)

Max Activating Token Index: 681

Text #17

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1294937 (The Pile)

Max Activating Token Index: 523

Text #18

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1785798 (The Pile)

Max Activating Token Index: 380

Text #19

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1929498 (The Pile)

Max Activating Token Index: 583