Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1653 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.7931. Min Range: -1.7931

Max Act: 1.7931. Min Act: -0.0000

Data Index: 858486 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 1.7931. Min Range: -1.7931

Max Act: 1.5766. Min Act: -0.0000

Data Index: 659664 (The Pile)

Max Activating Token Index: 473

Text #2

Max Range: 1.7931. Min Range: -1.7931

Max Act: 1.5876. Min Act: -0.0000

Data Index: 1593750 (The Pile)

Max Activating Token Index: 909

Text #3

Max Range: 1.7931. Min Range: -1.7931

Max Act: 1.5409. Min Act: -0.0000

Data Index: 1122030 (The Pile)

Max Activating Token Index: 465

Text #4

Max Range: 1.7931. Min Range: -1.7931

Max Act: 1.4195. Min Act: -0.0000

Data Index: 280940 (The Pile)

Max Activating Token Index: 517

Text #5

Max Range: 1.7931. Min Range: -1.7931

Max Act: 1.5906. Min Act: -0.0000

Data Index: 100281 (The Pile)

Max Activating Token Index: 583

Text #6

Max Range: 1.7931. Min Range: -1.7931

Max Act: 1.3498. Min Act: -0.0000

Data Index: 927458 (The Pile)

Max Activating Token Index: 250

Text #7

Max Range: 1.7931. Min Range: -1.7931

Max Act: 1.0782. Min Act: -0.0000

Data Index: 1628854 (The Pile)

Max Activating Token Index: 333

Text #8

Max Range: 1.7931. Min Range: -1.7931

Max Act: 1.0574. Min Act: -0.0000

Data Index: 686363 (The Pile)

Max Activating Token Index: 248

Text #9

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.9801. Min Act: -0.0000

Data Index: 1702869 (The Pile)

Max Activating Token Index: 894

Text #10

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.7448. Min Act: -0.0000

Data Index: 634106 (The Pile)

Max Activating Token Index: 578

Text #11

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.6150. Min Act: -0.0000

Data Index: 875623 (The Pile)

Max Activating Token Index: 80

Text #12

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.6770. Min Act: -0.0000

Data Index: 874091 (The Pile)

Max Activating Token Index: 151

Text #13

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1897377 (The Pile)

Max Activating Token Index: 941

Text #14

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1604127 (The Pile)

Max Activating Token Index: 770

Text #15

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.5284. Min Act: 0.0000

Data Index: 28972 (The Pile)

Max Activating Token Index: 662

Text #16

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.5875. Min Act: -0.0000

Data Index: 513055 (The Pile)

Max Activating Token Index: 128

Text #17

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.5408. Min Act: 0.0000

Data Index: 1481497 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.4643. Min Act: -0.0000

Data Index: 1736483 (The Pile)

Max Activating Token Index: 845

Text #19

Max Range: 1.7931. Min Range: -1.7931

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1306235 (The Pile)

Max Activating Token Index: 496