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

Dataset: The Pile

Neuron 2850 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: 1.7754. Min Range: -1.7754

Max Act: 1.7754. Min Act: -0.0000

Data Index: 1602229 (The Pile)

Max Activating Token Index: 584

Text #1

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.5571. Min Act: -0.0000

Data Index: 1432678 (The Pile)

Max Activating Token Index: 196

Text #2

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.4576. Min Act: -0.0000

Data Index: 706390 (The Pile)

Max Activating Token Index: 175

Text #3

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.2293. Min Act: -0.0000

Data Index: 1774040 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.2904. Min Act: -0.0000

Data Index: 1545406 (The Pile)

Max Activating Token Index: 194

Text #5

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.3123. Min Act: -0.0000

Data Index: 990967 (The Pile)

Max Activating Token Index: 119

Text #6

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.2062. Min Act: -0.0000

Data Index: 871398 (The Pile)

Max Activating Token Index: 530

Text #7

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.2173. Min Act: -0.0000

Data Index: 1485541 (The Pile)

Max Activating Token Index: 170

Text #8

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.2086. Min Act: -0.0000

Data Index: 1818443 (The Pile)

Max Activating Token Index: 170

Text #9

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.1272. Min Act: -0.0000

Data Index: 1216163 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.1590. Min Act: -0.0000

Data Index: 1936356 (The Pile)

Max Activating Token Index: 758

Text #11

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.1354. Min Act: -0.0000

Data Index: 1656202 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.1329. Min Act: -0.0000

Data Index: 899964 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.0344. Min Act: -0.0000

Data Index: 480745 (The Pile)

Max Activating Token Index: 107

Text #14

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1295402 (The Pile)

Max Activating Token Index: 293

Text #15

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.1109. Min Act: -0.0000

Data Index: 481068 (The Pile)

Max Activating Token Index: 34

Text #16

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.0775. Min Act: -0.0000

Data Index: 79637 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.0705. Min Act: -0.0000

Data Index: 1270150 (The Pile)

Max Activating Token Index: 461

Text #18

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.1033. Min Act: -0.0000

Data Index: 1318549 (The Pile)

Max Activating Token Index: 273

Text #19

Max Range: 1.7754. Min Range: -1.7754

Max Act: 1.1309. Min Act: -0.0000

Data Index: 1387932 (The Pile)

Max Activating Token Index: 42