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

Dataset: The Pile

Neuron 4863 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: 0.9388. Min Range: -0.9388

Max Act: 0.9388. Min Act: 0.0000

Data Index: 62801 (The Pile)

Max Activating Token Index: 100

Text #1

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.6486. Min Act: -0.0000

Data Index: 782830 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1885927 (The Pile)

Max Activating Token Index: 254

Text #3

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1456619 (The Pile)

Max Activating Token Index: 647

Text #4

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.7012. Min Act: -0.0000

Data Index: 992684 (The Pile)

Max Activating Token Index: 542

Text #5

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1744738 (The Pile)

Max Activating Token Index: 51

Text #6

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.6400. Min Act: -0.0000

Data Index: 656705 (The Pile)

Max Activating Token Index: 489

Text #7

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5841. Min Act: -0.0000

Data Index: 330909 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5886. Min Act: -0.0000

Data Index: 39961 (The Pile)

Max Activating Token Index: 439

Text #9

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.6166. Min Act: 0.0000

Data Index: 808194 (The Pile)

Max Activating Token Index: 910

Text #10

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.6030. Min Act: -0.0000

Data Index: 1740619 (The Pile)

Max Activating Token Index: 354

Text #11

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1299106 (The Pile)

Max Activating Token Index: 220

Text #12

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1136020 (The Pile)

Max Activating Token Index: 552

Text #13

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1287228 (The Pile)

Max Activating Token Index: 591

Text #14

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5881. Min Act: 0.0000

Data Index: 1687188 (The Pile)

Max Activating Token Index: 782

Text #15

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1875382 (The Pile)

Max Activating Token Index: 962

Text #16

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1562035 (The Pile)

Max Activating Token Index: 961

Text #17

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5763. Min Act: 0.0000

Data Index: 1636204 (The Pile)

Max Activating Token Index: 48

Text #18

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5930. Min Act: -0.0000

Data Index: 690145 (The Pile)

Max Activating Token Index: 561

Text #19

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1023534 (The Pile)

Max Activating Token Index: 329