Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2564 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.9064. Min Act: -0.0001

Data Index: 1623180 (The Pile)

Max Activating Token Index: 406

Text #1

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.8158. Min Act: -0.0001

Data Index: 765675 (The Pile)

Max Activating Token Index: 602

Text #2

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7083. Min Act: -0.0001

Data Index: 34580 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7452. Min Act: -0.0000

Data Index: 1690770 (The Pile)

Max Activating Token Index: 948

Text #4

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7126. Min Act: -0.0000

Data Index: 271246 (The Pile)

Max Activating Token Index: 757

Text #5

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6709. Min Act: -0.0001

Data Index: 1372249 (The Pile)

Max Activating Token Index: 376

Text #6

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6829. Min Act: -0.0001

Data Index: 1617173 (The Pile)

Max Activating Token Index: 586

Text #7

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7027. Min Act: -0.0001

Data Index: 1787730 (The Pile)

Max Activating Token Index: 385

Text #8

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7144. Min Act: -0.0001

Data Index: 451264 (The Pile)

Max Activating Token Index: 546

Text #9

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6310. Min Act: -0.0001

Data Index: 343369 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6567. Min Act: -0.0001

Data Index: 1792710 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6389. Min Act: -0.0001

Data Index: 1721982 (The Pile)

Max Activating Token Index: 428

Text #12

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6793. Min Act: -0.0000

Data Index: 868483 (The Pile)

Max Activating Token Index: 815

Text #13

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6458. Min Act: -0.0001

Data Index: 143776 (The Pile)

Max Activating Token Index: 813

Text #14

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6136. Min Act: -0.0000

Data Index: 1234701 (The Pile)

Max Activating Token Index: 773

Text #15

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6539. Min Act: -0.0001

Data Index: 1075872 (The Pile)

Max Activating Token Index: 422

Text #16

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6285. Min Act: -0.0001

Data Index: 408149 (The Pile)

Max Activating Token Index: 291

Text #17

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6002. Min Act: -0.0001

Data Index: 642716 (The Pile)

Max Activating Token Index: 504

Text #18

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1399661 (The Pile)

Max Activating Token Index: 465

Text #19

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5940. Min Act: -0.0001

Data Index: 567281 (The Pile)

Max Activating Token Index: 313