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

Dataset: The Pile

Neuron 1625 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: 1.3569. Min Range: -1.3569

Max Act: 1.3204. Min Act: -0.0000

Data Index: 1347732 (The Pile)

Max Activating Token Index: 586

Text #1

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.3569. Min Act: -0.0000

Data Index: 679703 (The Pile)

Max Activating Token Index: 14

Text #2

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1986486 (The Pile)

Max Activating Token Index: 175

Text #3

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.2753. Min Act: -0.0000

Data Index: 407334 (The Pile)

Max Activating Token Index: 900

Text #4

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.2431. Min Act: -0.0000

Data Index: 250321 (The Pile)

Max Activating Token Index: 11

Text #5

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.1384. Min Act: -0.0000

Data Index: 1901223 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.1653. Min Act: -0.0000

Data Index: 1017759 (The Pile)

Max Activating Token Index: 899

Text #7

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.3088. Min Act: -0.0000

Data Index: 194719 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.2896. Min Act: -0.0000

Data Index: 162892 (The Pile)

Max Activating Token Index: 560

Text #9

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.2488. Min Act: -0.0000

Data Index: 439335 (The Pile)

Max Activating Token Index: 757

Text #10

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1674242 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.2265. Min Act: -0.0000

Data Index: 1525841 (The Pile)

Max Activating Token Index: 625

Text #12

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.0724. Min Act: -0.0000

Data Index: 1017298 (The Pile)

Max Activating Token Index: 1008

Text #13

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.1714. Min Act: -0.0000

Data Index: 758304 (The Pile)

Max Activating Token Index: 562

Text #14

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.2138. Min Act: -0.0000

Data Index: 787236 (The Pile)

Max Activating Token Index: 79

Text #15

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.2308. Min Act: -0.0000

Data Index: 1287302 (The Pile)

Max Activating Token Index: 258

Text #16

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.1443. Min Act: -0.0000

Data Index: 1775495 (The Pile)

Max Activating Token Index: 711

Text #17

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.1516. Min Act: -0.0000

Data Index: 646475 (The Pile)

Max Activating Token Index: 293

Text #18

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.1458. Min Act: -0.0000

Data Index: 250730 (The Pile)

Max Activating Token Index: 340

Text #19

Max Range: 1.3569. Min Range: -1.3569

Max Act: 1.0648. Min Act: -0.0000

Data Index: 904024 (The Pile)

Max Activating Token Index: 621