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

Dataset: The Pile

Neuron 4850 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: 0.5835. Min Range: -0.5835

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1576859 (The Pile)

Max Activating Token Index: 781

Text #1

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5660. Min Act: -0.0000

Data Index: 431639 (The Pile)

Max Activating Token Index: 960

Text #2

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5258. Min Act: -0.0000

Data Index: 1441079 (The Pile)

Max Activating Token Index: 568

Text #3

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5061. Min Act: 0.0000

Data Index: 512372 (The Pile)

Max Activating Token Index: 928

Text #4

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1364855 (The Pile)

Max Activating Token Index: 931

Text #5

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4716. Min Act: -0.0000

Data Index: 914676 (The Pile)

Max Activating Token Index: 919

Text #6

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4801. Min Act: -0.0000

Data Index: 695456 (The Pile)

Max Activating Token Index: 252

Text #7

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1158019 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4584. Min Act: -0.0000

Data Index: 457059 (The Pile)

Max Activating Token Index: 188

Text #9

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1089186 (The Pile)

Max Activating Token Index: 583

Text #10

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4582. Min Act: -0.0000

Data Index: 485460 (The Pile)

Max Activating Token Index: 662

Text #11

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1933561 (The Pile)

Max Activating Token Index: 630

Text #12

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1025705 (The Pile)

Max Activating Token Index: 83

Text #13

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1774454 (The Pile)

Max Activating Token Index: 194

Text #14

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4721. Min Act: -0.0000

Data Index: 367488 (The Pile)

Max Activating Token Index: 876

Text #15

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3881. Min Act: -0.0000

Data Index: 1393376 (The Pile)

Max Activating Token Index: 760

Text #16

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1853626 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1001097 (The Pile)

Max Activating Token Index: 690

Text #18

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4352. Min Act: -0.0000

Data Index: 524255 (The Pile)

Max Activating Token Index: 285

Text #19

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1787525 (The Pile)

Max Activating Token Index: 766