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

Dataset: The Pile

Neuron 4351 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.2326. Min Act: -0.0000

Data Index: 134155 (The Pile)

Max Activating Token Index: 736

Text #1

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3373. Min Act: -0.0000

Data Index: 102463 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3985. Min Act: -0.0000

Data Index: 568441 (The Pile)

Max Activating Token Index: 482

Text #3

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3415. Min Act: -0.0000

Data Index: 972695 (The Pile)

Max Activating Token Index: 644

Text #4

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3849. Min Act: -0.0000

Data Index: 589934 (The Pile)

Max Activating Token Index: 401

Text #5

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.1389. Min Act: -0.0000

Data Index: 894906 (The Pile)

Max Activating Token Index: 582

Text #6

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.0450. Min Act: -0.0000

Data Index: 1905870 (The Pile)

Max Activating Token Index: 755

Text #7

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.1099. Min Act: -0.0000

Data Index: 1724329 (The Pile)

Max Activating Token Index: 575

Text #8

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.1846. Min Act: -0.0000

Data Index: 1247221 (The Pile)

Max Activating Token Index: 903

Text #9

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.2528. Min Act: -0.0000

Data Index: 998839 (The Pile)

Max Activating Token Index: 569

Text #10

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.2644. Min Act: -0.0000

Data Index: 659876 (The Pile)

Max Activating Token Index: 818

Text #11

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.2264. Min Act: -0.0000

Data Index: 83990 (The Pile)

Max Activating Token Index: 741

Text #12

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.1278. Min Act: -0.0000

Data Index: 318156 (The Pile)

Max Activating Token Index: 209

Text #13

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.1377. Min Act: -0.0000

Data Index: 76022 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 1.3985. Min Range: -1.3985

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1217956 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.1134. Min Act: -0.0000

Data Index: 1167892 (The Pile)

Max Activating Token Index: 304

Text #16

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.1781. Min Act: -0.0000

Data Index: 68297 (The Pile)

Max Activating Token Index: 829

Text #17

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.2000. Min Act: -0.0000

Data Index: 1671933 (The Pile)

Max Activating Token Index: 813

Text #18

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.1087. Min Act: -0.0000

Data Index: 1646583 (The Pile)

Max Activating Token Index: 448

Text #19

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.1083. Min Act: -0.0000

Data Index: 594294 (The Pile)

Max Activating Token Index: 341