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

Dataset: The Pile

Neuron 4023 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: 0.3743. Min Range: -0.3743

Max Act: 0.3743. Min Act: -0.0000

Data Index: 943995 (The Pile)

Max Activating Token Index: 331

Text #1

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3233. Min Act: -0.0000

Data Index: 792598 (The Pile)

Max Activating Token Index: 311

Text #2

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1722586 (The Pile)

Max Activating Token Index: 306

Text #3

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2885. Min Act: -0.0000

Data Index: 305925 (The Pile)

Max Activating Token Index: 88

Text #4

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2722. Min Act: -0.0000

Data Index: 1160110 (The Pile)

Max Activating Token Index: 485

Text #5

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2634. Min Act: -0.0000

Data Index: 1139243 (The Pile)

Max Activating Token Index: 719

Text #6

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1658414 (The Pile)

Max Activating Token Index: 211

Text #7

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1805793 (The Pile)

Max Activating Token Index: 738

Text #8

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2470. Min Act: -0.0000

Data Index: 1771339 (The Pile)

Max Activating Token Index: 60

Text #9

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2340. Min Act: -0.0000

Data Index: 427288 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2488. Min Act: -0.0000

Data Index: 385591 (The Pile)

Max Activating Token Index: 145

Text #11

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2371. Min Act: -0.0000

Data Index: 425179 (The Pile)

Max Activating Token Index: 973

Text #12

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2436. Min Act: -0.0000

Data Index: 376457 (The Pile)

Max Activating Token Index: 597

Text #13

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2259. Min Act: -0.0000

Data Index: 26372 (The Pile)

Max Activating Token Index: 244

Text #14

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2525. Min Act: -0.0000

Data Index: 1341783 (The Pile)

Max Activating Token Index: 626

Text #15

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2222. Min Act: -0.0000

Data Index: 810750 (The Pile)

Max Activating Token Index: 485

Text #16

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2021. Min Act: -0.0000

Data Index: 79648 (The Pile)

Max Activating Token Index: 249

Text #17

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2240. Min Act: -0.0001

Data Index: 1580908 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1788478 (The Pile)

Max Activating Token Index: 407

Text #19

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1281411 (The Pile)

Max Activating Token Index: 383