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

Dataset: The Pile

Neuron 2396 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.4327. Min Act: -0.0000

Data Index: 1387553 (The Pile)

Max Activating Token Index: 326

Text #1

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.3999. Min Act: -0.0000

Data Index: 547613 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.2282. Min Act: -0.0000

Data Index: 292432 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.2996. Min Act: -0.0000

Data Index: 1640395 (The Pile)

Max Activating Token Index: 149

Text #4

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.2061. Min Act: -0.0000

Data Index: 1578109 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.4447. Min Act: -0.0000

Data Index: 839199 (The Pile)

Max Activating Token Index: 886

Text #6

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.2657. Min Act: -0.0000

Data Index: 540564 (The Pile)

Max Activating Token Index: 831

Text #7

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.2766. Min Act: -0.0000

Data Index: 529607 (The Pile)

Max Activating Token Index: 456

Text #8

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.1472. Min Act: -0.0000

Data Index: 125872 (The Pile)

Max Activating Token Index: 703

Text #9

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.2461. Min Act: -0.0000

Data Index: 525865 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.1069. Min Act: -0.0000

Data Index: 370154 (The Pile)

Max Activating Token Index: 58

Text #11

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.2199. Min Act: -0.0000

Data Index: 1902659 (The Pile)

Max Activating Token Index: 209

Text #12

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.1997. Min Act: -0.0000

Data Index: 1434667 (The Pile)

Max Activating Token Index: 433

Text #13

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.1250. Min Act: -0.0000

Data Index: 22752 (The Pile)

Max Activating Token Index: 230

Text #14

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.1550. Min Act: -0.0000

Data Index: 1143635 (The Pile)

Max Activating Token Index: 333

Text #15

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.1210. Min Act: -0.0000

Data Index: 762100 (The Pile)

Max Activating Token Index: 133

Text #16

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.0790. Min Act: -0.0000

Data Index: 1930540 (The Pile)

Max Activating Token Index: 627

Text #17

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.0800. Min Act: -0.0000

Data Index: 725119 (The Pile)

Max Activating Token Index: 935

Text #18

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.1535. Min Act: -0.0000

Data Index: 642886 (The Pile)

Max Activating Token Index: 877

Text #19

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1259149 (The Pile)

Max Activating Token Index: 763