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

Dataset: The Pile

Neuron 730 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.8853. Min Act: -0.0000

Data Index: 1932961 (The Pile)

Max Activating Token Index: 272

Text #1

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.3986. Min Act: -0.0000

Data Index: 1539257 (The Pile)

Max Activating Token Index: 790

Text #2

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.2676. Min Act: -0.0000

Data Index: 1003703 (The Pile)

Max Activating Token Index: 835

Text #3

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.2340. Min Act: -0.0000

Data Index: 1464464 (The Pile)

Max Activating Token Index: 418

Text #4

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.1278. Min Act: -0.0000

Data Index: 141093 (The Pile)

Max Activating Token Index: 161

Text #5

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.3631. Min Act: -0.0000

Data Index: 508747 (The Pile)

Max Activating Token Index: 624

Text #6

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.2423. Min Act: -0.0000

Data Index: 1922987 (The Pile)

Max Activating Token Index: 671

Text #7

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.0961. Min Act: -0.0000

Data Index: 825672 (The Pile)

Max Activating Token Index: 331

Text #8

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1614050 (The Pile)

Max Activating Token Index: 924

Text #9

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.1816. Min Act: -0.0000

Data Index: 279995 (The Pile)

Max Activating Token Index: 74

Text #10

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.1263. Min Act: -0.0000

Data Index: 271453 (The Pile)

Max Activating Token Index: 801

Text #11

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.0582. Min Act: -0.0000

Data Index: 586179 (The Pile)

Max Activating Token Index: 964

Text #12

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.0787. Min Act: -0.0000

Data Index: 1839161 (The Pile)

Max Activating Token Index: 506

Text #13

Max Range: 1.8853. Min Range: -1.8853

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1234789 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.0415. Min Act: -0.0000

Data Index: 1060228 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.0464. Min Act: -0.0000

Data Index: 1995462 (The Pile)

Max Activating Token Index: 518

Text #16

Max Range: 1.8853. Min Range: -1.8853

Max Act: 0.9708. Min Act: -0.0000

Data Index: 1444239 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 1.8853. Min Range: -1.8853

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1743261 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 1.8853. Min Range: -1.8853

Max Act: 0.8786. Min Act: -0.0000

Data Index: 1009189 (The Pile)

Max Activating Token Index: 728

Text #19

Max Range: 1.8853. Min Range: -1.8853

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1515354 (The Pile)

Max Activating Token Index: 826