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

Dataset: The Pile

Neuron 1822 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.8499. Min Act: -0.0000

Data Index: 658786 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1438372 (The Pile)

Max Activating Token Index: 902

Text #2

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6033. Min Act: -0.0000

Data Index: 115102 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6169. Min Act: -0.0000

Data Index: 227326 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5937. Min Act: -0.0000

Data Index: 1682906 (The Pile)

Max Activating Token Index: 189

Text #5

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5660. Min Act: -0.0000

Data Index: 937054 (The Pile)

Max Activating Token Index: 788

Text #6

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5547. Min Act: -0.0000

Data Index: 962376 (The Pile)

Max Activating Token Index: 940

Text #7

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5301. Min Act: -0.0000

Data Index: 1597042 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1935466 (The Pile)

Max Activating Token Index: 652

Text #9

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.4500. Min Act: -0.0000

Data Index: 722697 (The Pile)

Max Activating Token Index: 823

Text #10

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1536496 (The Pile)

Max Activating Token Index: 454

Text #11

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1559989 (The Pile)

Max Activating Token Index: 849

Text #12

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.4831. Min Act: -0.0000

Data Index: 706933 (The Pile)

Max Activating Token Index: 729

Text #13

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.4752. Min Act: -0.0000

Data Index: 827291 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1384971 (The Pile)

Max Activating Token Index: 562

Text #15

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1723304 (The Pile)

Max Activating Token Index: 417

Text #16

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1470049 (The Pile)

Max Activating Token Index: 317

Text #17

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.4447. Min Act: -0.0000

Data Index: 876606 (The Pile)

Max Activating Token Index: 917

Text #18

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5090. Min Act: -0.0000

Data Index: 931270 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1966783 (The Pile)

Max Activating Token Index: 1016