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

Dataset: The Pile

Neuron 614 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: 0.7029. Min Range: -0.7029

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1916008 (The Pile)

Max Activating Token Index: 542

Text #1

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.6923. Min Act: -0.0000

Data Index: 1636180 (The Pile)

Max Activating Token Index: 951

Text #2

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5245. Min Act: -0.0000

Data Index: 174379 (The Pile)

Max Activating Token Index: 583

Text #3

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1798481 (The Pile)

Max Activating Token Index: 691

Text #4

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.4951. Min Act: -0.0000

Data Index: 316751 (The Pile)

Max Activating Token Index: 905

Text #5

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1458751 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1222315 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.4822. Min Act: -0.0000

Data Index: 947687 (The Pile)

Max Activating Token Index: 371

Text #8

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.4034. Min Act: -0.0000

Data Index: 156159 (The Pile)

Max Activating Token Index: 155

Text #9

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1008669 (The Pile)

Max Activating Token Index: 975

Text #10

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.4311. Min Act: -0.0000

Data Index: 369990 (The Pile)

Max Activating Token Index: 225

Text #11

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.3918. Min Act: -0.0000

Data Index: 582834 (The Pile)

Max Activating Token Index: 386

Text #12

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.4184. Min Act: -0.0000

Data Index: 191226 (The Pile)

Max Activating Token Index: 941

Text #13

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.3762. Min Act: -0.0000

Data Index: 800309 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1101800 (The Pile)

Max Activating Token Index: 833

Text #15

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1800644 (The Pile)

Max Activating Token Index: 1012

Text #16

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1409999 (The Pile)

Max Activating Token Index: 194

Text #17

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1367080 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1780104 (The Pile)

Max Activating Token Index: 134

Text #19

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.3780. Min Act: -0.0000

Data Index: 992481 (The Pile)

Max Activating Token Index: 147