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

Dataset: The Pile

Neuron 887 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: 0.8663. Min Range: -0.8663

Max Act: 0.8663. Min Act: -0.0000

Data Index: 991370 (The Pile)

Max Activating Token Index: 351

Text #1

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1138015 (The Pile)

Max Activating Token Index: 99

Text #2

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.8272. Min Act: -0.0000

Data Index: 186813 (The Pile)

Max Activating Token Index: 707

Text #3

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1648226 (The Pile)

Max Activating Token Index: 261

Text #4

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1768075 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.7059. Min Act: -0.0000

Data Index: 56134 (The Pile)

Max Activating Token Index: 51

Text #6

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1563883 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6899. Min Act: -0.0000

Data Index: 463233 (The Pile)

Max Activating Token Index: 421

Text #8

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1536811 (The Pile)

Max Activating Token Index: 326

Text #9

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6645. Min Act: -0.0000

Data Index: 187246 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6625. Min Act: -0.0000

Data Index: 1652570 (The Pile)

Max Activating Token Index: 661

Text #11

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1766576 (The Pile)

Max Activating Token Index: 1006

Text #12

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6273. Min Act: -0.0000

Data Index: 814078 (The Pile)

Max Activating Token Index: 658

Text #13

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1323748 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6946. Min Act: -0.0000

Data Index: 57632 (The Pile)

Max Activating Token Index: 667

Text #15

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6006. Min Act: -0.0000

Data Index: 10163 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1550585 (The Pile)

Max Activating Token Index: 656

Text #17

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.6028. Min Act: -0.0000

Data Index: 495466 (The Pile)

Max Activating Token Index: 152

Text #18

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1880134 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 0.8663. Min Range: -0.8663

Max Act: 0.5939. Min Act: -0.0000

Data Index: 549361 (The Pile)

Max Activating Token Index: 707