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

Dataset: The Pile

Neuron 3055 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: 2.1992. Min Range: -2.1992

Max Act: 2.1992. Min Act: -0.0000

Data Index: 578841 (The Pile)

Max Activating Token Index: 381

Text #1

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.7973. Min Act: -0.0000

Data Index: 1986511 (The Pile)

Max Activating Token Index: 525

Text #2

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.9059. Min Act: -0.0000

Data Index: 1706960 (The Pile)

Max Activating Token Index: 574

Text #3

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.6596. Min Act: -0.0000

Data Index: 1413976 (The Pile)

Max Activating Token Index: 98

Text #4

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.7765. Min Act: -0.0000

Data Index: 1637487 (The Pile)

Max Activating Token Index: 617

Text #5

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.6879. Min Act: -0.0000

Data Index: 1915908 (The Pile)

Max Activating Token Index: 883

Text #6

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.7143. Min Act: -0.0000

Data Index: 670082 (The Pile)

Max Activating Token Index: 966

Text #7

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.6244. Min Act: -0.0000

Data Index: 1696783 (The Pile)

Max Activating Token Index: 156

Text #8

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.5155. Min Act: -0.0000

Data Index: 299068 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.5857. Min Act: -0.0000

Data Index: 169087 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.5918. Min Act: -0.0000

Data Index: 551591 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.5544. Min Act: -0.0000

Data Index: 1004925 (The Pile)

Max Activating Token Index: 54

Text #12

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.5452. Min Act: -0.0000

Data Index: 1189570 (The Pile)

Max Activating Token Index: 935

Text #13

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.5301. Min Act: -0.0000

Data Index: 1328509 (The Pile)

Max Activating Token Index: 684

Text #14

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.5203. Min Act: -0.0000

Data Index: 1862259 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.5065. Min Act: -0.0000

Data Index: 1005753 (The Pile)

Max Activating Token Index: 505

Text #16

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.4245. Min Act: -0.0000

Data Index: 1107116 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.5745. Min Act: -0.0000

Data Index: 891102 (The Pile)

Max Activating Token Index: 105

Text #18

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.4043. Min Act: -0.0000

Data Index: 911964 (The Pile)

Max Activating Token Index: 118

Text #19

Max Range: 2.1992. Min Range: -2.1992

Max Act: 1.4781. Min Act: -0.0000

Data Index: 1986624 (The Pile)

Max Activating Token Index: 380