Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3118 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.8012. Min Act: -0.0000

Data Index: 908336 (The Pile)

Max Activating Token Index: 192

Text #1

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1029436 (The Pile)

Max Activating Token Index: 116

Text #2

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.2282. Min Act: -0.0000

Data Index: 1751695 (The Pile)

Max Activating Token Index: 385

Text #3

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.1576. Min Act: -0.0000

Data Index: 633045 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.1017. Min Act: -0.0000

Data Index: 1335282 (The Pile)

Max Activating Token Index: 645

Text #5

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.0889. Min Act: -0.0000

Data Index: 1586597 (The Pile)

Max Activating Token Index: 876

Text #6

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1152107 (The Pile)

Max Activating Token Index: 984

Text #7

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.0721. Min Act: -0.0000

Data Index: 752382 (The Pile)

Max Activating Token Index: 1006

Text #8

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.0716. Min Act: -0.0000

Data Index: 1770121 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.0761. Min Act: -0.0000

Data Index: 809893 (The Pile)

Max Activating Token Index: 304

Text #10

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.0687. Min Act: -0.0000

Data Index: 212657 (The Pile)

Max Activating Token Index: 708

Text #11

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.0657. Min Act: -0.0000

Data Index: 550916 (The Pile)

Max Activating Token Index: 641

Text #12

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.0588. Min Act: -0.0000

Data Index: 474969 (The Pile)

Max Activating Token Index: 87

Text #13

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.0679. Min Act: -0.0000

Data Index: 954060 (The Pile)

Max Activating Token Index: 930

Text #14

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.0598. Min Act: -0.0000

Data Index: 989363 (The Pile)

Max Activating Token Index: 973

Text #15

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.0726. Min Act: -0.0000

Data Index: 751715 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.0671. Min Act: -0.0000

Data Index: 106389 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.0802. Min Act: -0.0000

Data Index: 1950638 (The Pile)

Max Activating Token Index: 494

Text #18

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.0608. Min Act: -0.0000

Data Index: 1468883 (The Pile)

Max Activating Token Index: 661

Text #19

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.0546. Min Act: -0.0000

Data Index: 838305 (The Pile)

Max Activating Token Index: 778