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

Dataset: The Pile

Neuron 1081 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: 0.1718. Min Range: -0.1718

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1903553 (The Pile)

Max Activating Token Index: 238

Text #1

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1684. Min Act: -0.0000

Data Index: 560182 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1950479 (The Pile)

Max Activating Token Index: 1015

Text #3

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1599286 (The Pile)

Max Activating Token Index: 282

Text #4

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1448. Min Act: -0.0000

Data Index: 972331 (The Pile)

Max Activating Token Index: 109

Text #5

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1536. Min Act: -0.0000

Data Index: 952590 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1467. Min Act: -0.0000

Data Index: 1276530 (The Pile)

Max Activating Token Index: 18

Text #7

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1931746 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1432. Min Act: -0.0000

Data Index: 662379 (The Pile)

Max Activating Token Index: 961

Text #9

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1358. Min Act: -0.0000

Data Index: 452701 (The Pile)

Max Activating Token Index: 499

Text #10

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1295. Min Act: -0.0000

Data Index: 396347 (The Pile)

Max Activating Token Index: 34

Text #11

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1650100 (The Pile)

Max Activating Token Index: 82

Text #12

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1435. Min Act: -0.0001

Data Index: 198402 (The Pile)

Max Activating Token Index: 700

Text #13

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1442. Min Act: -0.0000

Data Index: 1475504 (The Pile)

Max Activating Token Index: 821

Text #14

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1277. Min Act: -0.0000

Data Index: 1380053 (The Pile)

Max Activating Token Index: 47

Text #15

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1218784 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1272. Min Act: -0.0000

Data Index: 222908 (The Pile)

Max Activating Token Index: 332

Text #17

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1742473 (The Pile)

Max Activating Token Index: 185

Text #18

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1224. Min Act: -0.0000

Data Index: 239229 (The Pile)

Max Activating Token Index: 341

Text #19

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1171. Min Act: -0.0000

Data Index: 909186 (The Pile)

Max Activating Token Index: 316