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

Dataset: The Pile

Neuron 1829 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0125. Min Act: -0.0000

Data Index: 1742337 (The Pile)

Max Activating Token Index: 3

Text #1

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0123. Min Act: -0.0000

Data Index: 962679 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0120. Min Act: -0.0000

Data Index: 519783 (The Pile)

Max Activating Token Index: 7

Text #3

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0117. Min Act: -0.0000

Data Index: 757588 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0000

Data Index: 721899 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0119. Min Act: -0.0000

Data Index: 1097822 (The Pile)

Max Activating Token Index: 6

Text #6

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0114. Min Act: -0.0000

Data Index: 594461 (The Pile)

Max Activating Token Index: 13

Text #7

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0112. Min Act: -0.0000

Data Index: 1792411 (The Pile)

Max Activating Token Index: 4

Text #8

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0111. Min Act: -0.0000

Data Index: 734830 (The Pile)

Max Activating Token Index: 4

Text #9

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0110. Min Act: -0.0000

Data Index: 384474 (The Pile)

Max Activating Token Index: 15

Text #10

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0109. Min Act: -0.0000

Data Index: 1654562 (The Pile)

Max Activating Token Index: 6

Text #11

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0109. Min Act: -0.0000

Data Index: 86953 (The Pile)

Max Activating Token Index: 6

Text #12

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0109. Min Act: -0.0000

Data Index: 1541867 (The Pile)

Max Activating Token Index: 7

Text #13

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0109. Min Act: -0.0000

Data Index: 707527 (The Pile)

Max Activating Token Index: 6

Text #14

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0108. Min Act: -0.0000

Data Index: 1805912 (The Pile)

Max Activating Token Index: 3

Text #15

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0107. Min Act: -0.0000

Data Index: 1738130 (The Pile)

Max Activating Token Index: 5

Text #16

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0107. Min Act: -0.0000

Data Index: 744479 (The Pile)

Max Activating Token Index: 10

Text #17

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0107. Min Act: -0.0000

Data Index: 1311167 (The Pile)

Max Activating Token Index: 4

Text #18

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0105. Min Act: -0.0000

Data Index: 832490 (The Pile)

Max Activating Token Index: 9

Text #19

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0105. Min Act: -0.0000

Data Index: 793856 (The Pile)

Max Activating Token Index: 7