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

Dataset: The Pile

Neuron 1419 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: 1.1849. Min Range: -1.1849

Max Act: 1.1147. Min Act: -0.0000

Data Index: 1760343 (The Pile)

Max Activating Token Index: 681

Text #1

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.1849. Min Act: -0.0000

Data Index: 203196 (The Pile)

Max Activating Token Index: 875

Text #2

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.1808. Min Act: -0.0000

Data Index: 1043234 (The Pile)

Max Activating Token Index: 489

Text #3

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.0687. Min Act: -0.0000

Data Index: 858290 (The Pile)

Max Activating Token Index: 79

Text #4

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.0620. Min Act: -0.0000

Data Index: 1676481 (The Pile)

Max Activating Token Index: 235

Text #5

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.0869. Min Act: -0.0000

Data Index: 46390 (The Pile)

Max Activating Token Index: 432

Text #6

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1953565 (The Pile)

Max Activating Token Index: 105

Text #7

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1002428 (The Pile)

Max Activating Token Index: 222

Text #8

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.1078. Min Act: -0.0000

Data Index: 1188189 (The Pile)

Max Activating Token Index: 375

Text #9

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1918650 (The Pile)

Max Activating Token Index: 531

Text #10

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.0283. Min Act: -0.0000

Data Index: 1466815 (The Pile)

Max Activating Token Index: 259

Text #11

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1950958 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1551858 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.9245. Min Act: -0.0000

Data Index: 615887 (The Pile)

Max Activating Token Index: 564

Text #14

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.0150. Min Act: 0.0000

Data Index: 709091 (The Pile)

Max Activating Token Index: 813

Text #15

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1178692 (The Pile)

Max Activating Token Index: 596

Text #16

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.0476. Min Act: -0.0000

Data Index: 1377485 (The Pile)

Max Activating Token Index: 404

Text #17

Max Range: 1.1849. Min Range: -1.1849

Max Act: 1.0130. Min Act: -0.0000

Data Index: 1677616 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1357713 (The Pile)

Max Activating Token Index: 795

Text #19

Max Range: 1.1849. Min Range: -1.1849

Max Act: 0.9531. Min Act: -0.0000

Data Index: 17219 (The Pile)

Max Activating Token Index: 424