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

Dataset: The Pile

Neuron 3390 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.7771. Min Act: -0.0000

Data Index: 482294 (The Pile)

Max Activating Token Index: 164

Text #1

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6463. Min Act: -0.0000

Data Index: 1069117 (The Pile)

Max Activating Token Index: 914

Text #2

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6810. Min Act: -0.0000

Data Index: 1067142 (The Pile)

Max Activating Token Index: 453

Text #3

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6820. Min Act: -0.0000

Data Index: 1630874 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.7707. Min Act: -0.0000

Data Index: 1943409 (The Pile)

Max Activating Token Index: 739

Text #5

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6166. Min Act: -0.0000

Data Index: 1258114 (The Pile)

Max Activating Token Index: 952

Text #6

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.5238. Min Act: -0.0000

Data Index: 166073 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.5119. Min Act: -0.0000

Data Index: 875761 (The Pile)

Max Activating Token Index: 120

Text #8

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.5544. Min Act: -0.0000

Data Index: 1742533 (The Pile)

Max Activating Token Index: 919

Text #9

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.4835. Min Act: -0.0000

Data Index: 279543 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.5812. Min Act: -0.0000

Data Index: 1600721 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.4705. Min Act: -0.0000

Data Index: 1078750 (The Pile)

Max Activating Token Index: 170

Text #12

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.4855. Min Act: -0.0000

Data Index: 1732998 (The Pile)

Max Activating Token Index: 217

Text #13

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.5655. Min Act: -0.0000

Data Index: 1538672 (The Pile)

Max Activating Token Index: 315

Text #14

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.5066. Min Act: -0.0000

Data Index: 1097160 (The Pile)

Max Activating Token Index: 676

Text #15

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.3155. Min Act: -0.0000

Data Index: 1532656 (The Pile)

Max Activating Token Index: 223

Text #16

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.4650. Min Act: -0.0000

Data Index: 1341479 (The Pile)

Max Activating Token Index: 990

Text #17

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.4108. Min Act: -0.0000

Data Index: 568899 (The Pile)

Max Activating Token Index: 943

Text #18

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.4227. Min Act: -0.0000

Data Index: 3835 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.4771. Min Act: -0.0000

Data Index: 834928 (The Pile)

Max Activating Token Index: 803