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

Dataset: The Pile

Neuron 2747 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: 0.9530. Min Range: -0.9530

Max Act: 0.9530. Min Act: -0.0000

Data Index: 282082 (The Pile)

Max Activating Token Index: 300

Text #1

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.8554. Min Act: -0.0000

Data Index: 1851828 (The Pile)

Max Activating Token Index: 963

Text #2

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.9081. Min Act: -0.0000

Data Index: 1332800 (The Pile)

Max Activating Token Index: 586

Text #3

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.8275. Min Act: -0.0000

Data Index: 239672 (The Pile)

Max Activating Token Index: 987

Text #4

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.9014. Min Act: -0.0000

Data Index: 1702345 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.8824. Min Act: -0.0000

Data Index: 884870 (The Pile)

Max Activating Token Index: 152

Text #6

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.8965. Min Act: -0.0000

Data Index: 882530 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.8114. Min Act: -0.0000

Data Index: 1329260 (The Pile)

Max Activating Token Index: 854

Text #8

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.8282. Min Act: -0.0000

Data Index: 996446 (The Pile)

Max Activating Token Index: 750

Text #9

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.8010. Min Act: -0.0000

Data Index: 281746 (The Pile)

Max Activating Token Index: 750

Text #10

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1179442 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1213428 (The Pile)

Max Activating Token Index: 342

Text #12

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1206114 (The Pile)

Max Activating Token Index: 546

Text #13

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.7542. Min Act: -0.0000

Data Index: 1689538 (The Pile)

Max Activating Token Index: 190

Text #14

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1663714 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.7149. Min Act: -0.0000

Data Index: 534055 (The Pile)

Max Activating Token Index: 936

Text #16

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.7163. Min Act: -0.0000

Data Index: 563592 (The Pile)

Max Activating Token Index: 49

Text #17

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.7381. Min Act: -0.0000

Data Index: 483297 (The Pile)

Max Activating Token Index: 1001

Text #18

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.6632. Min Act: -0.0000

Data Index: 438220 (The Pile)

Max Activating Token Index: 309

Text #19

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.7165. Min Act: -0.0000

Data Index: 783566 (The Pile)

Max Activating Token Index: 115