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

Dataset: The Pile

Neuron 150 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.9883. Min Act: -0.0000

Data Index: 658358 (The Pile)

Max Activating Token Index: 407

Text #1

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1330853 (The Pile)

Max Activating Token Index: 721

Text #2

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1015060 (The Pile)

Max Activating Token Index: 352

Text #3

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1936705 (The Pile)

Max Activating Token Index: 765

Text #4

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.9297. Min Act: -0.0000

Data Index: 361312 (The Pile)

Max Activating Token Index: 931

Text #5

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8498. Min Act: -0.0000

Data Index: 34275 (The Pile)

Max Activating Token Index: 32

Text #6

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8992. Min Act: -0.0000

Data Index: 1299222 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1974294 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1575500 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1152388 (The Pile)

Max Activating Token Index: 784

Text #10

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7503. Min Act: -0.0000

Data Index: 929662 (The Pile)

Max Activating Token Index: 264

Text #11

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6701. Min Act: -0.0000

Data Index: 659713 (The Pile)

Max Activating Token Index: 827

Text #12

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7870. Min Act: -0.0000

Data Index: 1331671 (The Pile)

Max Activating Token Index: 46

Text #13

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7791. Min Act: -0.0000

Data Index: 340727 (The Pile)

Max Activating Token Index: 291

Text #14

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8143. Min Act: -0.0000

Data Index: 586296 (The Pile)

Max Activating Token Index: 608

Text #15

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7695. Min Act: -0.0000

Data Index: 558881 (The Pile)

Max Activating Token Index: 643

Text #16

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1380142 (The Pile)

Max Activating Token Index: 117

Text #17

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7609. Min Act: -0.0000

Data Index: 439471 (The Pile)

Max Activating Token Index: 58

Text #18

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1365044 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1639685 (The Pile)

Max Activating Token Index: 683