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

Dataset: The Pile

Neuron 147 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: 1.1531. Min Range: -1.1531

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1917400 (The Pile)

Max Activating Token Index: 833

Text #1

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.0032. Min Act: -0.0000

Data Index: 1588841 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.1531. Min Act: -0.0000

Data Index: 1022243 (The Pile)

Max Activating Token Index: 802

Text #3

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.1018. Min Act: -0.0000

Data Index: 1908914 (The Pile)

Max Activating Token Index: 102

Text #4

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.0003. Min Act: -0.0000

Data Index: 951102 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9740. Min Act: -0.0000

Data Index: 744883 (The Pile)

Max Activating Token Index: 920

Text #6

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9300. Min Act: -0.0000

Data Index: 1592503 (The Pile)

Max Activating Token Index: 706

Text #7

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9904. Min Act: -0.0000

Data Index: 1790512 (The Pile)

Max Activating Token Index: 732

Text #8

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.0192. Min Act: -0.0000

Data Index: 1658586 (The Pile)

Max Activating Token Index: 803

Text #9

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9551. Min Act: -0.0000

Data Index: 1451594 (The Pile)

Max Activating Token Index: 535

Text #10

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1421690 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9458. Min Act: -0.0000

Data Index: 320084 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9550. Min Act: -0.0000

Data Index: 644424 (The Pile)

Max Activating Token Index: 411

Text #13

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9581. Min Act: -0.0000

Data Index: 371311 (The Pile)

Max Activating Token Index: 495

Text #14

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.0407. Min Act: -0.0000

Data Index: 582129 (The Pile)

Max Activating Token Index: 997

Text #15

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8961. Min Act: -0.0000

Data Index: 828019 (The Pile)

Max Activating Token Index: 810

Text #16

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9197. Min Act: -0.0000

Data Index: 108014 (The Pile)

Max Activating Token Index: 236

Text #17

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9140. Min Act: -0.0000

Data Index: 1086464 (The Pile)

Max Activating Token Index: 928

Text #18

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1418065 (The Pile)

Max Activating Token Index: 797

Text #19

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9127. Min Act: -0.0000

Data Index: 1289395 (The Pile)

Max Activating Token Index: 390