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

Dataset: The Pile

Neuron 1034 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0290. Min Range: -1.0290

Max Act: 1.0290. Min Act: -0.0000

Data Index: 279578 (The Pile)

Max Activating Token Index: 455

Text #1

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1493165 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1205670 (The Pile)

Max Activating Token Index: 290

Text #3

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.5747. Min Act: -0.0000

Data Index: 494916 (The Pile)

Max Activating Token Index: 13

Text #4

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.5069. Min Act: -0.0000

Data Index: 844696 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.4467. Min Act: -0.0000

Data Index: 351639 (The Pile)

Max Activating Token Index: 742

Text #6

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.4809. Min Act: -0.0000

Data Index: 169205 (The Pile)

Max Activating Token Index: 953

Text #7

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.4862. Min Act: -0.0000

Data Index: 854068 (The Pile)

Max Activating Token Index: 905

Text #8

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1165661 (The Pile)

Max Activating Token Index: 315

Text #9

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.4811. Min Act: -0.0000

Data Index: 628672 (The Pile)

Max Activating Token Index: 558

Text #10

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1482873 (The Pile)

Max Activating Token Index: 351

Text #11

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.4096. Min Act: -0.0000

Data Index: 568495 (The Pile)

Max Activating Token Index: 678

Text #12

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.4288. Min Act: -0.0000

Data Index: 492536 (The Pile)

Max Activating Token Index: 672

Text #13

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.3955. Min Act: -0.0000

Data Index: 720158 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1205759 (The Pile)

Max Activating Token Index: 424

Text #15

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.3775. Min Act: -0.0000

Data Index: 1852523 (The Pile)

Max Activating Token Index: 331

Text #16

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1727113 (The Pile)

Max Activating Token Index: 1002

Text #17

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.3820. Min Act: -0.0000

Data Index: 361789 (The Pile)

Max Activating Token Index: 914

Text #18

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1272981 (The Pile)

Max Activating Token Index: 1004

Text #19

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1777248 (The Pile)

Max Activating Token Index: 902