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

Dataset: The Pile

Neuron 2879 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1851. Min Act: -0.0000

Data Index: 1866094 (The Pile)

Max Activating Token Index: 937

Text #1

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1992788 (The Pile)

Max Activating Token Index: 636

Text #2

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1489. Min Act: -0.0000

Data Index: 184988 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1280. Min Act: -0.0000

Data Index: 549853 (The Pile)

Max Activating Token Index: 970

Text #4

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1768553 (The Pile)

Max Activating Token Index: 303

Text #5

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1366. Min Act: -0.0000

Data Index: 1652297 (The Pile)

Max Activating Token Index: 718

Text #6

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1417. Min Act: -0.0000

Data Index: 1367107 (The Pile)

Max Activating Token Index: 409

Text #7

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1300. Min Act: -0.0000

Data Index: 1537633 (The Pile)

Max Activating Token Index: 205

Text #8

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1350. Min Act: -0.0000

Data Index: 117738 (The Pile)

Max Activating Token Index: 321

Text #9

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1508512 (The Pile)

Max Activating Token Index: 667

Text #10

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1197588 (The Pile)

Max Activating Token Index: 970

Text #11

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1208. Min Act: -0.0000

Data Index: 8671 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1237. Min Act: -0.0000

Data Index: 216748 (The Pile)

Max Activating Token Index: 432

Text #13

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1226. Min Act: -0.0000

Data Index: 715939 (The Pile)

Max Activating Token Index: 777

Text #14

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1329. Min Act: -0.0000

Data Index: 1878041 (The Pile)

Max Activating Token Index: 399

Text #15

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1783316 (The Pile)

Max Activating Token Index: 447

Text #16

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1605231 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1181. Min Act: -0.0000

Data Index: 225573 (The Pile)

Max Activating Token Index: 864

Text #18

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1199. Min Act: -0.0000

Data Index: 1832997 (The Pile)

Max Activating Token Index: 701

Text #19

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1288. Min Act: -0.0000

Data Index: 824706 (The Pile)

Max Activating Token Index: 350