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

Dataset: The Pile

Neuron 1637 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1718877 (The Pile)

Max Activating Token Index: 233

Text #1

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.9611. Min Act: -0.0000

Data Index: 318975 (The Pile)

Max Activating Token Index: 671

Text #2

Max Range: 1.0372. Min Range: -1.0372

Max Act: 1.0372. Min Act: -0.0000

Data Index: 1465483 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.9464. Min Act: -0.0000

Data Index: 33660 (The Pile)

Max Activating Token Index: 508

Text #4

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.9024. Min Act: -0.0000

Data Index: 169435 (The Pile)

Max Activating Token Index: 122

Text #5

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.9025. Min Act: -0.0000

Data Index: 1138020 (The Pile)

Max Activating Token Index: 190

Text #6

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1136643 (The Pile)

Max Activating Token Index: 129

Text #7

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.8635. Min Act: -0.0000

Data Index: 189894 (The Pile)

Max Activating Token Index: 667

Text #8

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.9190. Min Act: -0.0000

Data Index: 409738 (The Pile)

Max Activating Token Index: 283

Text #9

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.8159. Min Act: -0.0000

Data Index: 1920757 (The Pile)

Max Activating Token Index: 654

Text #10

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.8021. Min Act: -0.0000

Data Index: 781487 (The Pile)

Max Activating Token Index: 99

Text #11

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6637. Min Act: -0.0000

Data Index: 40276 (The Pile)

Max Activating Token Index: 666

Text #12

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.9189. Min Act: -0.0000

Data Index: 634168 (The Pile)

Max Activating Token Index: 147

Text #13

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.8101. Min Act: -0.0000

Data Index: 352730 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.8479. Min Act: -0.0000

Data Index: 270349 (The Pile)

Max Activating Token Index: 727

Text #15

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7765. Min Act: -0.0000

Data Index: 384777 (The Pile)

Max Activating Token Index: 987

Text #16

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1667328 (The Pile)

Max Activating Token Index: 122

Text #17

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1018198 (The Pile)

Max Activating Token Index: 767

Text #18

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7700. Min Act: -0.0000

Data Index: 1369791 (The Pile)

Max Activating Token Index: 95

Text #19

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.8047. Min Act: -0.0000

Data Index: 292811 (The Pile)

Max Activating Token Index: 80