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

Dataset: The Pile

Neuron 1117 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1499331 (The Pile)

Max Activating Token Index: 243

Text #1

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1163931 (The Pile)

Max Activating Token Index: 65

Text #2

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1074. Min Act: -0.0000

Data Index: 821993 (The Pile)

Max Activating Token Index: 816

Text #3

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0921. Min Act: -0.0000

Data Index: 360340 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.1025. Min Act: -0.0000

Data Index: 684048 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0909. Min Act: -0.0000

Data Index: 1489230 (The Pile)

Max Activating Token Index: 924

Text #6

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0991. Min Act: -0.0000

Data Index: 323824 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0955. Min Act: -0.0000

Data Index: 14547 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1352072 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1174942 (The Pile)

Max Activating Token Index: 419

Text #10

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1499923 (The Pile)

Max Activating Token Index: 891

Text #11

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0864. Min Act: -0.0000

Data Index: 498383 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1791190 (The Pile)

Max Activating Token Index: 409

Text #13

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0862. Min Act: -0.0000

Data Index: 660649 (The Pile)

Max Activating Token Index: 358

Text #14

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0994. Min Act: -0.0000

Data Index: 815785 (The Pile)

Max Activating Token Index: 942

Text #15

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0907. Min Act: -0.0000

Data Index: 788633 (The Pile)

Max Activating Token Index: 605

Text #16

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1463385 (The Pile)

Max Activating Token Index: 291

Text #17

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0859. Min Act: -0.0000

Data Index: 672531 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0882. Min Act: -0.0000

Data Index: 208647 (The Pile)

Max Activating Token Index: 876

Text #19

Max Range: 0.1315. Min Range: -0.1315

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1943112 (The Pile)

Max Activating Token Index: 947