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

Dataset: The Pile

Neuron 1362 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: 0.6100. Min Range: -0.6100

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1651659 (The Pile)

Max Activating Token Index: 645

Text #1

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5366. Min Act: 0.0000

Data Index: 129913 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4140. Min Act: -0.0000

Data Index: 86700 (The Pile)

Max Activating Token Index: 811

Text #3

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3699. Min Act: 0.0000

Data Index: 1181642 (The Pile)

Max Activating Token Index: 606

Text #4

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1928994 (The Pile)

Max Activating Token Index: 672

Text #5

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1618569 (The Pile)

Max Activating Token Index: 895

Text #6

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3764. Min Act: -0.0000

Data Index: 296594 (The Pile)

Max Activating Token Index: 989

Text #7

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3621. Min Act: -0.0000

Data Index: 564121 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1888597 (The Pile)

Max Activating Token Index: 492

Text #9

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3689. Min Act: 0.0001

Data Index: 1276872 (The Pile)

Max Activating Token Index: 589

Text #10

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1146603 (The Pile)

Max Activating Token Index: 511

Text #11

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3497. Min Act: -0.0000

Data Index: 533158 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3373. Min Act: -0.0000

Data Index: 300383 (The Pile)

Max Activating Token Index: 940

Text #13

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1193721 (The Pile)

Max Activating Token Index: 421

Text #14

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3439. Min Act: -0.0000

Data Index: 123691 (The Pile)

Max Activating Token Index: 823

Text #15

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1219423 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3307. Min Act: -0.0000

Data Index: 513454 (The Pile)

Max Activating Token Index: 970

Text #17

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1950091 (The Pile)

Max Activating Token Index: 406

Text #18

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1159590 (The Pile)

Max Activating Token Index: 267

Text #19

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3309. Min Act: -0.0000

Data Index: 17167 (The Pile)

Max Activating Token Index: 786