Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1560 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.8063. Min Act: -0.0000

Data Index: 804965 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7836. Min Act: -0.0000

Data Index: 1352065 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.7797. Min Act: -0.0000

Data Index: 390959 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.6878. Min Act: -0.0000

Data Index: 172035 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.6624. Min Act: -0.0000

Data Index: 967673 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.6566. Min Act: -0.0000

Data Index: 1102561 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.6973. Min Act: -0.0000

Data Index: 1244842 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.6235. Min Act: -0.0000

Data Index: 1364460 (Python Code)

Max Activating Token Index: 771

Text #8

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.5807. Min Act: -0.0000

Data Index: 548877 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.4240. Min Act: -0.0000

Data Index: 195031 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.4222. Min Act: -0.0000

Data Index: 354955 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.4858. Min Act: -0.0000

Data Index: 1630120 (Python Code)

Max Activating Token Index: 338

Text #12

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.3944. Min Act: -0.0000

Data Index: 1085544 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.4426. Min Act: -0.0000

Data Index: 862083 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.4370. Min Act: -0.0000

Data Index: 1182472 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.4284. Min Act: -0.0000

Data Index: 751493 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.3910. Min Act: -0.0000

Data Index: 486421 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.3986. Min Act: -0.0000

Data Index: 103584 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.3846. Min Act: -0.0000

Data Index: 1211353 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.3100. Min Act: -0.0000

Data Index: 631685 (C4 (Web Text))

Max Activating Token Index: 796