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

Dataset: The Pile

Neuron 2679 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: 0.8006. Min Range: -0.8006

Max Act: 0.7964. Min Act: -0.0000

Data Index: 1662910 (The Pile)

Max Activating Token Index: 864

Text #1

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1031032 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1096486 (The Pile)

Max Activating Token Index: 832

Text #3

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1562540 (The Pile)

Max Activating Token Index: 302

Text #4

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7848. Min Act: -0.0000

Data Index: 210854 (The Pile)

Max Activating Token Index: 767

Text #5

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7121. Min Act: -0.0000

Data Index: 489091 (The Pile)

Max Activating Token Index: 765

Text #6

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1951023 (The Pile)

Max Activating Token Index: 806

Text #7

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1754796 (The Pile)

Max Activating Token Index: 992

Text #8

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1241075 (The Pile)

Max Activating Token Index: 19

Text #9

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7235. Min Act: -0.0000

Data Index: 982601 (The Pile)

Max Activating Token Index: 213

Text #10

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7033. Min Act: -0.0000

Data Index: 866421 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1892455 (The Pile)

Max Activating Token Index: 690

Text #12

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6923. Min Act: -0.0000

Data Index: 992303 (The Pile)

Max Activating Token Index: 478

Text #13

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6887. Min Act: -0.0000

Data Index: 375895 (The Pile)

Max Activating Token Index: 498

Text #14

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6613. Min Act: -0.0000

Data Index: 102536 (The Pile)

Max Activating Token Index: 800

Text #15

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6703. Min Act: -0.0000

Data Index: 1045459 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6281. Min Act: -0.0000

Data Index: 1608270 (The Pile)

Max Activating Token Index: 827

Text #17

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1713333 (The Pile)

Max Activating Token Index: 468

Text #18

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1778759 (The Pile)

Max Activating Token Index: 609

Text #19

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6410. Min Act: -0.0001

Data Index: 1602170 (The Pile)

Max Activating Token Index: 827