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

Dataset: The Pile

Neuron 39 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: 0.8112. Min Range: -0.8112

Max Act: 0.8112. Min Act: -0.0000

Data Index: 845740 (The Pile)

Max Activating Token Index: 504

Text #1

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.7229. Min Act: -0.0000

Data Index: 803631 (The Pile)

Max Activating Token Index: 869

Text #2

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1285880 (The Pile)

Max Activating Token Index: 488

Text #3

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.7374. Min Act: -0.0000

Data Index: 1383460 (The Pile)

Max Activating Token Index: 591

Text #4

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.7025. Min Act: -0.0000

Data Index: 311030 (The Pile)

Max Activating Token Index: 518

Text #5

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.7124. Min Act: -0.0000

Data Index: 673433 (The Pile)

Max Activating Token Index: 639

Text #6

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6578. Min Act: -0.0000

Data Index: 27377 (The Pile)

Max Activating Token Index: 249

Text #7

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6512. Min Act: -0.0000

Data Index: 500072 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1338230 (The Pile)

Max Activating Token Index: 631

Text #9

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1843689 (The Pile)

Max Activating Token Index: 110

Text #10

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6302. Min Act: -0.0000

Data Index: 343468 (The Pile)

Max Activating Token Index: 875

Text #11

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5705. Min Act: -0.0000

Data Index: 1781823 (The Pile)

Max Activating Token Index: 905

Text #12

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1994098 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1471558 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1646218 (The Pile)

Max Activating Token Index: 522

Text #15

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1757130 (The Pile)

Max Activating Token Index: 458

Text #16

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5210. Min Act: -0.0000

Data Index: 1236224 (The Pile)

Max Activating Token Index: 930

Text #17

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1595326 (The Pile)

Max Activating Token Index: 467

Text #18

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1784037 (The Pile)

Max Activating Token Index: 155

Text #19

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5532. Min Act: -0.0000

Data Index: 72348 (The Pile)

Max Activating Token Index: 664