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

Dataset: The Pile

Neuron 788 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.7440. Min Act: -0.0000

Data Index: 35798 (The Pile)

Max Activating Token Index: 624

Text #1

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1944646 (The Pile)

Max Activating Token Index: 303

Text #2

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4866. Min Act: -0.0000

Data Index: 88461 (The Pile)

Max Activating Token Index: 764

Text #3

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1997111 (The Pile)

Max Activating Token Index: 984

Text #4

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1171045 (The Pile)

Max Activating Token Index: 372

Text #5

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4866. Min Act: -0.0000

Data Index: 1082451 (The Pile)

Max Activating Token Index: 837

Text #6

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1896376 (The Pile)

Max Activating Token Index: 975

Text #7

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1407123 (The Pile)

Max Activating Token Index: 925

Text #8

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1595577 (The Pile)

Max Activating Token Index: 470

Text #9

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4221. Min Act: -0.0000

Data Index: 607409 (The Pile)

Max Activating Token Index: 757

Text #10

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1261717 (The Pile)

Max Activating Token Index: 206

Text #11

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.3838. Min Act: -0.0000

Data Index: 633611 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.3559. Min Act: -0.0000

Data Index: 1036731 (The Pile)

Max Activating Token Index: 203

Text #13

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1599801 (The Pile)

Max Activating Token Index: 727

Text #14

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.3970. Min Act: -0.0000

Data Index: 948573 (The Pile)

Max Activating Token Index: 469

Text #15

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.3381. Min Act: -0.0000

Data Index: 1638744 (The Pile)

Max Activating Token Index: 730

Text #16

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1038579 (The Pile)

Max Activating Token Index: 874

Text #17

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.3252. Min Act: -0.0000

Data Index: 503828 (The Pile)

Max Activating Token Index: 179

Text #18

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.3105. Min Act: -0.0000

Data Index: 868135 (The Pile)

Max Activating Token Index: 256

Text #19

Max Range: 0.7440. Min Range: -0.7440

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1754363 (The Pile)

Max Activating Token Index: 778