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

Dataset: The Pile

Neuron 3843 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9827. Min Range: -3.9827

Max Act: 3.9827. Min Act: -0.0000

Data Index: 858281 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 3.9827. Min Range: -3.9827

Max Act: 3.8354. Min Act: -0.0000

Data Index: 1524143 (The Pile)

Max Activating Token Index: 197

Text #2

Max Range: 3.9827. Min Range: -3.9827

Max Act: 3.5970. Min Act: -0.0000

Data Index: 214432 (The Pile)

Max Activating Token Index: 505

Text #3

Max Range: 3.9827. Min Range: -3.9827

Max Act: 3.1957. Min Act: -0.0000

Data Index: 587178 (The Pile)

Max Activating Token Index: 910

Text #4

Max Range: 3.9827. Min Range: -3.9827

Max Act: 3.5988. Min Act: -0.0000

Data Index: 1554566 (The Pile)

Max Activating Token Index: 667

Text #5

Max Range: 3.9827. Min Range: -3.9827

Max Act: 3.3259. Min Act: -0.0000

Data Index: 433324 (The Pile)

Max Activating Token Index: 307

Text #6

Max Range: 3.9827. Min Range: -3.9827

Max Act: 3.3209. Min Act: -0.0000

Data Index: 416341 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 3.9827. Min Range: -3.9827

Max Act: 3.4709. Min Act: -0.0000

Data Index: 782786 (The Pile)

Max Activating Token Index: 36

Text #8

Max Range: 3.9827. Min Range: -3.9827

Max Act: 3.2995. Min Act: -0.0000

Data Index: 1097439 (The Pile)

Max Activating Token Index: 372

Text #9

Max Range: 3.9827. Min Range: -3.9827

Max Act: 3.2784. Min Act: -0.0000

Data Index: 876148 (The Pile)

Max Activating Token Index: 360

Text #10

Max Range: 3.9827. Min Range: -3.9827

Max Act: 3.3980. Min Act: -0.0000

Data Index: 1635206 (The Pile)

Max Activating Token Index: 864

Text #11

Max Range: 3.9827. Min Range: -3.9827

Max Act: 3.3783. Min Act: -0.0000

Data Index: 61771 (The Pile)

Max Activating Token Index: 902

Text #12

Max Range: 3.9827. Min Range: -3.9827

Max Act: 2.9503. Min Act: -0.0000

Data Index: 13694 (The Pile)

Max Activating Token Index: 902

Text #13

Max Range: 3.9827. Min Range: -3.9827

Max Act: 3.0598. Min Act: -0.0000

Data Index: 226121 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 3.9827. Min Range: -3.9827

Max Act: 2.8445. Min Act: -0.0000

Data Index: 1901605 (The Pile)

Max Activating Token Index: 483

Text #15

Max Range: 3.9827. Min Range: -3.9827

Max Act: 2.8166. Min Act: -0.0000

Data Index: 1587031 (The Pile)

Max Activating Token Index: 168

Text #16

Max Range: 3.9827. Min Range: -3.9827

Max Act: 2.7901. Min Act: -0.0000

Data Index: 244981 (The Pile)

Max Activating Token Index: 945

Text #17

Max Range: 3.9827. Min Range: -3.9827

Max Act: 2.8006. Min Act: -0.0000

Data Index: 1836126 (The Pile)

Max Activating Token Index: 959

Text #18

Max Range: 3.9827. Min Range: -3.9827

Max Act: 2.8798. Min Act: -0.0000

Data Index: 763899 (The Pile)

Max Activating Token Index: 683

Text #19

Max Range: 3.9827. Min Range: -3.9827

Max Act: 2.8497. Min Act: -0.0000

Data Index: 1924814 (The Pile)

Max Activating Token Index: 892