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

Dataset: The Pile

Neuron 3534 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.2502. Min Act: -0.0000

Data Index: 1677332 (The Pile)

Max Activating Token Index: 781

Text #1

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.1811. Min Act: -0.0000

Data Index: 1489404 (The Pile)

Max Activating Token Index: 135

Text #2

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0630. Min Act: -0.0000

Data Index: 760285 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0575. Min Act: -0.0000

Data Index: 511616 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0844. Min Act: -0.0000

Data Index: 1459879 (The Pile)

Max Activating Token Index: 185

Text #5

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0489. Min Act: -0.0000

Data Index: 568136 (The Pile)

Max Activating Token Index: 525

Text #6

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0220. Min Act: -0.0000

Data Index: 1575642 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0563. Min Act: -0.0000

Data Index: 1073933 (The Pile)

Max Activating Token Index: 668

Text #8

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0485. Min Act: -0.0000

Data Index: 1498420 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.9986. Min Act: -0.0000

Data Index: 170911 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0083. Min Act: -0.0000

Data Index: 337942 (The Pile)

Max Activating Token Index: 375

Text #11

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0488. Min Act: -0.0000

Data Index: 1029062 (The Pile)

Max Activating Token Index: 214

Text #12

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1449328 (The Pile)

Max Activating Token Index: 470

Text #13

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0569. Min Act: -0.0000

Data Index: 1252701 (The Pile)

Max Activating Token Index: 564

Text #14

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.9954. Min Act: -0.0000

Data Index: 1944080 (The Pile)

Max Activating Token Index: 909

Text #15

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.9873. Min Act: -0.0000

Data Index: 1137939 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.9662. Min Act: -0.0000

Data Index: 1172864 (The Pile)

Max Activating Token Index: 332

Text #17

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1870816 (The Pile)

Max Activating Token Index: 144

Text #18

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1395902 (The Pile)

Max Activating Token Index: 431

Text #19

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1182461 (The Pile)

Max Activating Token Index: 227