Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2526 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2752. Min Act: -0.0001

Data Index: 1834234 (The Pile)

Max Activating Token Index: 340

Text #1

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1629045 (The Pile)

Max Activating Token Index: 76

Text #2

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1554. Min Act: -0.0000

Data Index: 708185 (The Pile)

Max Activating Token Index: 307

Text #3

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1425342 (The Pile)

Max Activating Token Index: 473

Text #4

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1753. Min Act: -0.0000

Data Index: 43580 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1468. Min Act: -0.0000

Data Index: 853979 (The Pile)

Max Activating Token Index: 162

Text #6

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1286. Min Act: -0.0000

Data Index: 877743 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1446. Min Act: -0.0000

Data Index: 1205456 (The Pile)

Max Activating Token Index: 361

Text #8

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1390. Min Act: -0.0000

Data Index: 1513152 (The Pile)

Max Activating Token Index: 209

Text #9

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1364. Min Act: -0.0000

Data Index: 961785 (The Pile)

Max Activating Token Index: 734

Text #10

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1388. Min Act: -0.0000

Data Index: 398092 (The Pile)

Max Activating Token Index: 409

Text #11

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1236. Min Act: -0.0000

Data Index: 384732 (The Pile)

Max Activating Token Index: 849

Text #12

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1526866 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1288. Min Act: -0.0000

Data Index: 101240 (The Pile)

Max Activating Token Index: 426

Text #14

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1706805 (The Pile)

Max Activating Token Index: 648

Text #15

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1201. Min Act: -0.0000

Data Index: 89805 (The Pile)

Max Activating Token Index: 559

Text #16

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1063687 (The Pile)

Max Activating Token Index: 985

Text #17

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1544312 (The Pile)

Max Activating Token Index: 562

Text #18

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1590252 (The Pile)

Max Activating Token Index: 566

Text #19

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1188. Min Act: -0.0000

Data Index: 124976 (The Pile)

Max Activating Token Index: 597