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

Dataset: The Pile

Neuron 3880 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.9141. Min Act: -0.0000

Data Index: 1294754 (The Pile)

Max Activating Token Index: 785

Text #1

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.8564. Min Act: -0.0000

Data Index: 1834183 (The Pile)

Max Activating Token Index: 673

Text #2

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.8110. Min Act: -0.0000

Data Index: 677443 (The Pile)

Max Activating Token Index: 672

Text #3

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.7992. Min Act: -0.0000

Data Index: 520585 (The Pile)

Max Activating Token Index: 407

Text #4

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1823561 (The Pile)

Max Activating Token Index: 499

Text #5

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.7494. Min Act: -0.0000

Data Index: 1923349 (The Pile)

Max Activating Token Index: 221

Text #6

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1982970 (The Pile)

Max Activating Token Index: 243

Text #7

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1966199 (The Pile)

Max Activating Token Index: 745

Text #8

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.7424. Min Act: -0.0000

Data Index: 1415840 (The Pile)

Max Activating Token Index: 527

Text #9

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1687673 (The Pile)

Max Activating Token Index: 800

Text #10

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1115600 (The Pile)

Max Activating Token Index: 986

Text #11

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1594390 (The Pile)

Max Activating Token Index: 857

Text #12

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5602. Min Act: -0.0000

Data Index: 366244 (The Pile)

Max Activating Token Index: 971

Text #13

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5110. Min Act: -0.0000

Data Index: 8066 (The Pile)

Max Activating Token Index: 908

Text #14

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.4789. Min Act: -0.0000

Data Index: 188376 (The Pile)

Max Activating Token Index: 767

Text #15

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.4987. Min Act: -0.0000

Data Index: 1670004 (The Pile)

Max Activating Token Index: 775

Text #16

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.4746. Min Act: -0.0000

Data Index: 555489 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.4270. Min Act: -0.0000

Data Index: 206281 (The Pile)

Max Activating Token Index: 826

Text #18

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1249469 (The Pile)

Max Activating Token Index: 832

Text #19

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.4159. Min Act: -0.0000

Data Index: 159813 (The Pile)

Max Activating Token Index: 660