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

Dataset: The Pile

Neuron 329 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: 1.5154. Min Range: -1.5154

Max Act: 1.5154. Min Act: -0.0000

Data Index: 364469 (The Pile)

Max Activating Token Index: 382

Text #1

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.9721. Min Act: -0.0000

Data Index: 1093333 (The Pile)

Max Activating Token Index: 869

Text #2

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1080. Min Act: -0.0000

Data Index: 1408177 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.0614. Min Act: -0.0000

Data Index: 1300459 (The Pile)

Max Activating Token Index: 785

Text #4

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.8471. Min Act: -0.0000

Data Index: 501384 (The Pile)

Max Activating Token Index: 98

Text #5

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1202782 (The Pile)

Max Activating Token Index: 436

Text #6

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1448607 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.7870. Min Act: -0.0000

Data Index: 304298 (The Pile)

Max Activating Token Index: 788

Text #8

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1605345 (The Pile)

Max Activating Token Index: 824

Text #9

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.7482. Min Act: -0.0000

Data Index: 842469 (The Pile)

Max Activating Token Index: 903

Text #10

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1168025 (The Pile)

Max Activating Token Index: 150

Text #11

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1008188 (The Pile)

Max Activating Token Index: 1001

Text #12

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1285485 (The Pile)

Max Activating Token Index: 783

Text #13

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.7537. Min Act: -0.0000

Data Index: 1800134 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.7261. Min Act: -0.0000

Data Index: 368296 (The Pile)

Max Activating Token Index: 652

Text #15

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.7534. Min Act: -0.0000

Data Index: 328190 (The Pile)

Max Activating Token Index: 563

Text #16

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1509282 (The Pile)

Max Activating Token Index: 851

Text #17

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.6641. Min Act: -0.0000

Data Index: 755127 (The Pile)

Max Activating Token Index: 659

Text #18

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.6696. Min Act: -0.0000

Data Index: 464349 (The Pile)

Max Activating Token Index: 364

Text #19

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1936798 (The Pile)

Max Activating Token Index: 619