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

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

Neuron 4353 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.7775. Min Act: -0.0001

Data Index: 973634 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.5781. Min Act: -0.0001

Data Index: 822923 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.5824. Min Act: -0.0001

Data Index: 139375 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.4464. Min Act: -0.0001

Data Index: 865641 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.5463. Min Act: -0.0001

Data Index: 431075 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.1918. Min Act: -0.0001

Data Index: 1228223 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.3100. Min Act: -0.0001

Data Index: 366773 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.1113. Min Act: -0.0001

Data Index: 1318220 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.2591. Min Act: -0.0001

Data Index: 449209 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 7.7775. Min Range: -7.7775

Max Act: 6.7055. Min Act: -0.0001

Data Index: 31407 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.2157. Min Act: -0.0001

Data Index: 618282 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.2008. Min Act: -0.0001

Data Index: 742449 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.1889. Min Act: -0.0001

Data Index: 949669 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.5009. Min Act: -0.0001

Data Index: 449293 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.2894. Min Act: -0.0001

Data Index: 500926 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 7.7775. Min Range: -7.7775

Max Act: 6.7701. Min Act: -0.0001

Data Index: 1030230 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.2703. Min Act: -0.0001

Data Index: 437146 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.0767. Min Act: -0.0001

Data Index: 503498 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 7.7775. Min Range: -7.7775

Max Act: 6.1514. Min Act: -0.0001

Data Index: 1178025 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 7.7775. Min Range: -7.7775

Max Act: 7.0685. Min Act: -0.0001

Data Index: 696543 (C4 (Web Text))

Max Activating Token Index: 30