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

Dataset: The Pile

Neuron 3743 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: 1.3578. Min Range: -1.3578

Max Act: 1.3293. Min Act: -0.0000

Data Index: 916582 (The Pile)

Max Activating Token Index: 524

Text #1

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.1778. Min Act: -0.0000

Data Index: 449628 (The Pile)

Max Activating Token Index: 828

Text #2

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.2742. Min Act: -0.0000

Data Index: 1959700 (The Pile)

Max Activating Token Index: 549

Text #3

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.2452. Min Act: -0.0000

Data Index: 1445929 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.1544. Min Act: -0.0000

Data Index: 1649708 (The Pile)

Max Activating Token Index: 532

Text #5

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.0787. Min Act: -0.0000

Data Index: 1593396 (The Pile)

Max Activating Token Index: 115

Text #6

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.3578. Min Act: -0.0000

Data Index: 273961 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.1234. Min Act: -0.0000

Data Index: 769756 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.9940. Min Act: -0.0000

Data Index: 876156 (The Pile)

Max Activating Token Index: 405

Text #9

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.0175. Min Act: -0.0000

Data Index: 795764 (The Pile)

Max Activating Token Index: 569

Text #10

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.0870. Min Act: -0.0000

Data Index: 594640 (The Pile)

Max Activating Token Index: 292

Text #11

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.9017. Min Act: -0.0000

Data Index: 1075615 (The Pile)

Max Activating Token Index: 730

Text #12

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.9783. Min Act: -0.0000

Data Index: 274810 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.9487. Min Act: -0.0000

Data Index: 15826 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.9531. Min Act: -0.0000

Data Index: 1735099 (The Pile)

Max Activating Token Index: 966

Text #15

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1369068 (The Pile)

Max Activating Token Index: 845

Text #16

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.9621. Min Act: -0.0000

Data Index: 644212 (The Pile)

Max Activating Token Index: 282

Text #17

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1565141 (The Pile)

Max Activating Token Index: 759

Text #18

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.8187. Min Act: -0.0000

Data Index: 1252662 (The Pile)

Max Activating Token Index: 575

Text #19

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.7881. Min Act: -0.0000

Data Index: 308459 (The Pile)

Max Activating Token Index: 530