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

Dataset: The Pile

Neuron 2643 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: 0.3089. Min Range: -0.3089

Max Act: 0.3089. Min Act: -0.0000

Data Index: 867492 (The Pile)

Max Activating Token Index: 1012

Text #1

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1150569 (The Pile)

Max Activating Token Index: 504

Text #2

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2683. Min Act: -0.0000

Data Index: 81466 (The Pile)

Max Activating Token Index: 985

Text #3

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2546. Min Act: -0.0000

Data Index: 190212 (The Pile)

Max Activating Token Index: 902

Text #4

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2478. Min Act: -0.0000

Data Index: 722103 (The Pile)

Max Activating Token Index: 979

Text #5

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2750. Min Act: -0.0000

Data Index: 671450 (The Pile)

Max Activating Token Index: 757

Text #6

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1455591 (The Pile)

Max Activating Token Index: 812

Text #7

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1255255 (The Pile)

Max Activating Token Index: 1017

Text #8

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2445. Min Act: -0.0000

Data Index: 199326 (The Pile)

Max Activating Token Index: 9

Text #9

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1312385 (The Pile)

Max Activating Token Index: 731

Text #10

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2735. Min Act: -0.0000

Data Index: 670895 (The Pile)

Max Activating Token Index: 298

Text #11

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1992029 (The Pile)

Max Activating Token Index: 811

Text #12

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1592279 (The Pile)

Max Activating Token Index: 554

Text #13

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2213. Min Act: -0.0000

Data Index: 534374 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2153. Min Act: -0.0000

Data Index: 1964719 (The Pile)

Max Activating Token Index: 907

Text #15

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2036. Min Act: -0.0000

Data Index: 930373 (The Pile)

Max Activating Token Index: 258

Text #16

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1937622 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1780770 (The Pile)

Max Activating Token Index: 681

Text #18

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1568169 (The Pile)

Max Activating Token Index: 121

Text #19

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2008. Min Act: -0.0000

Data Index: 1703098 (The Pile)

Max Activating Token Index: 863