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

Dataset: The Pile

Neuron 1933 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: 0.5465. Min Range: -0.5465

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1778109 (The Pile)

Max Activating Token Index: 998

Text #1

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.5281. Min Act: -0.0000

Data Index: 365829 (The Pile)

Max Activating Token Index: 975

Text #2

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4732. Min Act: -0.0000

Data Index: 503132 (The Pile)

Max Activating Token Index: 883

Text #3

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.5465. Min Act: -0.0000

Data Index: 589654 (The Pile)

Max Activating Token Index: 783

Text #4

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4685. Min Act: -0.0000

Data Index: 182011 (The Pile)

Max Activating Token Index: 743

Text #5

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4662. Min Act: -0.0000

Data Index: 869126 (The Pile)

Max Activating Token Index: 856

Text #6

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4181. Min Act: -0.0000

Data Index: 952375 (The Pile)

Max Activating Token Index: 971

Text #7

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1423015 (The Pile)

Max Activating Token Index: 520

Text #8

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4563. Min Act: -0.0000

Data Index: 158519 (The Pile)

Max Activating Token Index: 995

Text #9

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4691. Min Act: -0.0000

Data Index: 525978 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4844. Min Act: -0.0000

Data Index: 88588 (The Pile)

Max Activating Token Index: 998

Text #11

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4460. Min Act: -0.0000

Data Index: 459174 (The Pile)

Max Activating Token Index: 637

Text #12

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4434. Min Act: -0.0000

Data Index: 375121 (The Pile)

Max Activating Token Index: 476

Text #13

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1617182 (The Pile)

Max Activating Token Index: 727

Text #14

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4714. Min Act: -0.0000

Data Index: 112420 (The Pile)

Max Activating Token Index: 714

Text #15

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4729. Min Act: -0.0000

Data Index: 501792 (The Pile)

Max Activating Token Index: 1018

Text #16

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1142883 (The Pile)

Max Activating Token Index: 450

Text #17

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1669912 (The Pile)

Max Activating Token Index: 965

Text #18

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1230607 (The Pile)

Max Activating Token Index: 777

Text #19

Max Range: 0.5465. Min Range: -0.5465

Max Act: 0.4767. Min Act: -0.0000

Data Index: 740522 (The Pile)

Max Activating Token Index: 1023