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

Dataset: The Pile

Neuron 5078 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: 0.6620. Min Range: -0.6620

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1579256 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.6620. Min Act: -0.0000

Data Index: 211460 (The Pile)

Max Activating Token Index: 1004

Text #2

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1225145 (The Pile)

Max Activating Token Index: 975

Text #3

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1948232 (The Pile)

Max Activating Token Index: 841

Text #4

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1725529 (The Pile)

Max Activating Token Index: 1020

Text #5

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1896848 (The Pile)

Max Activating Token Index: 221

Text #6

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1116134 (The Pile)

Max Activating Token Index: 982

Text #7

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1608843 (The Pile)

Max Activating Token Index: 988

Text #8

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4646. Min Act: -0.0000

Data Index: 458455 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4292. Min Act: -0.0000

Data Index: 988679 (The Pile)

Max Activating Token Index: 943

Text #10

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4274. Min Act: -0.0000

Data Index: 674000 (The Pile)

Max Activating Token Index: 704

Text #11

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4249. Min Act: -0.0000

Data Index: 88855 (The Pile)

Max Activating Token Index: 914

Text #12

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4153. Min Act: -0.0000

Data Index: 840822 (The Pile)

Max Activating Token Index: 968

Text #13

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.4318. Min Act: -0.0000

Data Index: 179799 (The Pile)

Max Activating Token Index: 330

Text #14

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.3950. Min Act: -0.0000

Data Index: 777871 (The Pile)

Max Activating Token Index: 243

Text #15

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1355245 (The Pile)

Max Activating Token Index: 869

Text #16

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1859037 (The Pile)

Max Activating Token Index: 634

Text #17

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.3318. Min Act: -0.0000

Data Index: 1369287 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.3307. Min Act: -0.0000

Data Index: 864643 (The Pile)

Max Activating Token Index: 319

Text #19

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1185126 (The Pile)

Max Activating Token Index: 758