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

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

Neuron 233 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3728. Min Act: -0.0000

Data Index: 987697 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.1523. Min Act: -0.0000

Data Index: 154087 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.1864. Min Act: -0.0000

Data Index: 105552 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.1651. Min Act: -0.0000

Data Index: 1340303 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.0693. Min Act: -0.0000

Data Index: 1172566 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.1581. Min Act: -0.0000

Data Index: 1117740 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.0097. Min Act: -0.0000

Data Index: 302353 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1051643 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.0007. Min Act: -0.0000

Data Index: 71958 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.9640. Min Act: -0.0000

Data Index: 885589 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.9938. Min Act: -0.0000

Data Index: 349964 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.9652. Min Act: -0.0000

Data Index: 969701 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.0010. Min Act: -0.0000

Data Index: 1185837 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.9399. Min Act: -0.0000

Data Index: 211385 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.1047. Min Act: -0.0000

Data Index: 958079 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.8539. Min Act: -0.0000

Data Index: 808833 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1250126 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.8766. Min Act: -0.0000

Data Index: 599330 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.8868. Min Act: -0.0000

Data Index: 804933 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.9167. Min Act: -0.0000

Data Index: 917611 (C4 (Web Text))

Max Activating Token Index: 289