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

Dataset: The Pile

Neuron 2086 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3556. Min Range: -3.3556

Max Act: 3.3556. Min Act: -0.0000

Data Index: 1405038 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 3.3556. Min Range: -3.3556

Max Act: 2.6907. Min Act: -0.0000

Data Index: 1183731 (The Pile)

Max Activating Token Index: 141

Text #2

Max Range: 3.3556. Min Range: -3.3556

Max Act: 2.5801. Min Act: -0.0000

Data Index: 579190 (The Pile)

Max Activating Token Index: 310

Text #3

Max Range: 3.3556. Min Range: -3.3556

Max Act: 2.2578. Min Act: -0.0000

Data Index: 129431 (The Pile)

Max Activating Token Index: 150

Text #4

Max Range: 3.3556. Min Range: -3.3556

Max Act: 2.4586. Min Act: -0.0000

Data Index: 689224 (The Pile)

Max Activating Token Index: 65

Text #5

Max Range: 3.3556. Min Range: -3.3556

Max Act: 2.4045. Min Act: -0.0000

Data Index: 1768316 (The Pile)

Max Activating Token Index: 593

Text #6

Max Range: 3.3556. Min Range: -3.3556

Max Act: 2.2555. Min Act: -0.0000

Data Index: 365033 (The Pile)

Max Activating Token Index: 581

Text #7

Max Range: 3.3556. Min Range: -3.3556

Max Act: 2.3219. Min Act: -0.0000

Data Index: 441952 (The Pile)

Max Activating Token Index: 911

Text #8

Max Range: 3.3556. Min Range: -3.3556

Max Act: 2.1783. Min Act: -0.0000

Data Index: 1739596 (The Pile)

Max Activating Token Index: 171

Text #9

Max Range: 3.3556. Min Range: -3.3556

Max Act: 2.2616. Min Act: -0.0000

Data Index: 1264603 (The Pile)

Max Activating Token Index: 336

Text #10

Max Range: 3.3556. Min Range: -3.3556

Max Act: 2.1389. Min Act: -0.0000

Data Index: 1925274 (The Pile)

Max Activating Token Index: 529

Text #11

Max Range: 3.3556. Min Range: -3.3556

Max Act: 1.9310. Min Act: -0.0000

Data Index: 957228 (The Pile)

Max Activating Token Index: 118

Text #12

Max Range: 3.3556. Min Range: -3.3556

Max Act: 2.0648. Min Act: 0.0001

Data Index: 1090095 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 3.3556. Min Range: -3.3556

Max Act: 2.0463. Min Act: -0.0000

Data Index: 1381593 (The Pile)

Max Activating Token Index: 434

Text #14

Max Range: 3.3556. Min Range: -3.3556

Max Act: 1.9991. Min Act: -0.0000

Data Index: 151738 (The Pile)

Max Activating Token Index: 280

Text #15

Max Range: 3.3556. Min Range: -3.3556

Max Act: 1.9817. Min Act: -0.0000

Data Index: 288568 (The Pile)

Max Activating Token Index: 531

Text #16

Max Range: 3.3556. Min Range: -3.3556

Max Act: 1.8792. Min Act: -0.0000

Data Index: 349481 (The Pile)

Max Activating Token Index: 720

Text #17

Max Range: 3.3556. Min Range: -3.3556

Max Act: 1.8059. Min Act: -0.0000

Data Index: 1813478 (The Pile)

Max Activating Token Index: 636

Text #18

Max Range: 3.3556. Min Range: -3.3556

Max Act: 1.9117. Min Act: -0.0000

Data Index: 1335440 (The Pile)

Max Activating Token Index: 394

Text #19

Max Range: 3.3556. Min Range: -3.3556

Max Act: 1.9006. Min Act: -0.0000

Data Index: 862436 (The Pile)

Max Activating Token Index: 462