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

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

Neuron 4934 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.1416. Min Act: -0.0000

Data Index: 976982 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.3584. Min Act: -0.0000

Data Index: 464114 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.1166. Min Act: -0.0000

Data Index: 763858 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.1070. Min Act: -0.0000

Data Index: 453813 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.3675. Min Act: -0.0000

Data Index: 794052 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 3.3675. Min Range: -3.3675

Max Act: 2.9147. Min Act: -0.0001

Data Index: 18895 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2988. Min Act: -0.0000

Data Index: 425522 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 3.3675. Min Range: -3.3675

Max Act: 2.8091. Min Act: -0.0000

Data Index: 980827 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 3.3675. Min Range: -3.3675

Max Act: 2.8110. Min Act: -0.0000

Data Index: 140015 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 3.3675. Min Range: -3.3675

Max Act: 2.8013. Min Act: -0.0001

Data Index: 318756 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 3.3675. Min Range: -3.3675

Max Act: 2.9284. Min Act: -0.0000

Data Index: 1241859 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 3.3675. Min Range: -3.3675

Max Act: 2.6917. Min Act: -0.0000

Data Index: 1093058 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 3.3675. Min Range: -3.3675

Max Act: 2.4854. Min Act: -0.0000

Data Index: 297342 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 3.3675. Min Range: -3.3675

Max Act: 2.6081. Min Act: -0.0001

Data Index: 388514 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 3.3675. Min Range: -3.3675

Max Act: 2.6622. Min Act: -0.0001

Data Index: 1229025 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 3.3675. Min Range: -3.3675

Max Act: 2.5240. Min Act: -0.0001

Data Index: 1146792 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 3.3675. Min Range: -3.3675

Max Act: 2.5016. Min Act: -0.0000

Data Index: 229811 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 3.3675. Min Range: -3.3675

Max Act: 2.6345. Min Act: -0.0000

Data Index: 446016 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 3.3675. Min Range: -3.3675

Max Act: 2.5304. Min Act: -0.0000

Data Index: 559600 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 3.3675. Min Range: -3.3675

Max Act: 2.4803. Min Act: -0.0000

Data Index: 1253205 (C4 (Web Text))

Max Activating Token Index: 453