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

Dataset: The Pile

Neuron 3690 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: 1.2268. Min Range: -1.2268

Max Act: 1.2268. Min Act: -0.0000

Data Index: 73550 (The Pile)

Max Activating Token Index: 71

Text #1

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1730135 (The Pile)

Max Activating Token Index: 68

Text #2

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.0182. Min Act: -0.0000

Data Index: 1479091 (The Pile)

Max Activating Token Index: 701

Text #3

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.9390. Min Act: -0.0000

Data Index: 1695803 (The Pile)

Max Activating Token Index: 575

Text #4

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1036651 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.9071. Min Act: -0.0000

Data Index: 200252 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.9016. Min Act: -0.0000

Data Index: 1741637 (The Pile)

Max Activating Token Index: 249

Text #7

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1132912 (The Pile)

Max Activating Token Index: 597

Text #8

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.8582. Min Act: -0.0000

Data Index: 1082625 (The Pile)

Max Activating Token Index: 161

Text #9

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.8876. Min Act: -0.0000

Data Index: 717852 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1537757 (The Pile)

Max Activating Token Index: 373

Text #11

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.9060. Min Act: -0.0000

Data Index: 1803522 (The Pile)

Max Activating Token Index: 897

Text #12

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.8104. Min Act: -0.0000

Data Index: 1232973 (The Pile)

Max Activating Token Index: 32

Text #13

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1827756 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.8628. Min Act: -0.0000

Data Index: 597877 (The Pile)

Max Activating Token Index: 465

Text #15

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.7446. Min Act: -0.0000

Data Index: 11341 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.7642. Min Act: -0.0000

Data Index: 735614 (The Pile)

Max Activating Token Index: 43

Text #17

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1997957 (The Pile)

Max Activating Token Index: 505

Text #18

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.8617. Min Act: -0.0000

Data Index: 188418 (The Pile)

Max Activating Token Index: 189

Text #19

Max Range: 1.2268. Min Range: -1.2268

Max Act: 0.7727. Min Act: -0.0000

Data Index: 772980 (The Pile)

Max Activating Token Index: 562