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

Dataset: The Pile

Neuron 1028 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: 0.2783. Min Range: -0.2783

Max Act: 0.2783. Min Act: -0.0000

Data Index: 959549 (The Pile)

Max Activating Token Index: 650

Text #1

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1861293 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1227041 (The Pile)

Max Activating Token Index: 110

Text #3

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2403. Min Act: -0.0000

Data Index: 1539936 (The Pile)

Max Activating Token Index: 78

Text #4

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2429. Min Act: -0.0000

Data Index: 959816 (The Pile)

Max Activating Token Index: 328

Text #5

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2050. Min Act: -0.0000

Data Index: 387140 (The Pile)

Max Activating Token Index: 704

Text #6

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1496806 (The Pile)

Max Activating Token Index: 153

Text #7

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2250. Min Act: -0.0000

Data Index: 771499 (The Pile)

Max Activating Token Index: 205

Text #8

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2139. Min Act: -0.0000

Data Index: 999086 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2121. Min Act: -0.0000

Data Index: 619636 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.1996. Min Act: -0.0000

Data Index: 579551 (The Pile)

Max Activating Token Index: 135

Text #11

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2050. Min Act: -0.0000

Data Index: 265260 (The Pile)

Max Activating Token Index: 53

Text #12

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2181. Min Act: -0.0000

Data Index: 690175 (The Pile)

Max Activating Token Index: 552

Text #13

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1580337 (The Pile)

Max Activating Token Index: 110

Text #14

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1055527 (The Pile)

Max Activating Token Index: 790

Text #15

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2021. Min Act: -0.0000

Data Index: 865702 (The Pile)

Max Activating Token Index: 848

Text #16

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1082422 (The Pile)

Max Activating Token Index: 55

Text #17

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.1978. Min Act: -0.0000

Data Index: 707448 (The Pile)

Max Activating Token Index: 960

Text #18

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.1939. Min Act: -0.0000

Data Index: 787456 (The Pile)

Max Activating Token Index: 534

Text #19

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.1953. Min Act: -0.0000

Data Index: 755235 (The Pile)

Max Activating Token Index: 39