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

Dataset: The Pile

Neuron 1396 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: 1.5526. Min Range: -1.5526

Max Act: 1.5526. Min Act: -0.0000

Data Index: 1619464 (The Pile)

Max Activating Token Index: 661

Text #1

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.5300. Min Act: -0.0000

Data Index: 920061 (The Pile)

Max Activating Token Index: 284

Text #2

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.2409. Min Act: -0.0000

Data Index: 1967350 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.2799. Min Act: -0.0000

Data Index: 1088388 (The Pile)

Max Activating Token Index: 800

Text #4

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.3354. Min Act: -0.0000

Data Index: 1501757 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.3285. Min Act: -0.0000

Data Index: 1384325 (The Pile)

Max Activating Token Index: 3

Text #6

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.1834. Min Act: -0.0000

Data Index: 1969690 (The Pile)

Max Activating Token Index: 1021

Text #7

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.2457. Min Act: -0.0000

Data Index: 797664 (The Pile)

Max Activating Token Index: 728

Text #8

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.1191. Min Act: -0.0000

Data Index: 783772 (The Pile)

Max Activating Token Index: 967

Text #9

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.1691. Min Act: -0.0000

Data Index: 921810 (The Pile)

Max Activating Token Index: 365

Text #10

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.2055. Min Act: -0.0000

Data Index: 708590 (The Pile)

Max Activating Token Index: 1011

Text #11

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.1706. Min Act: -0.0000

Data Index: 1932137 (The Pile)

Max Activating Token Index: 296

Text #12

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.2300. Min Act: -0.0000

Data Index: 1021820 (The Pile)

Max Activating Token Index: 1000

Text #13

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.1834. Min Act: -0.0000

Data Index: 468570 (The Pile)

Max Activating Token Index: 957

Text #14

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.2968. Min Act: -0.0000

Data Index: 1841203 (The Pile)

Max Activating Token Index: 550

Text #15

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.2067. Min Act: -0.0000

Data Index: 1504014 (The Pile)

Max Activating Token Index: 595

Text #16

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.0992. Min Act: -0.0000

Data Index: 622717 (The Pile)

Max Activating Token Index: 886

Text #17

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.0668. Min Act: -0.0000

Data Index: 1178623 (The Pile)

Max Activating Token Index: 825

Text #18

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.1230. Min Act: -0.0000

Data Index: 1018898 (The Pile)

Max Activating Token Index: 191

Text #19

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.1419. Min Act: -0.0000

Data Index: 1317913 (The Pile)

Max Activating Token Index: 911