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

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

Neuron 284 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.3073. Min Act: -0.0000

Data Index: 1297712 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.0932. Min Act: -0.0000

Data Index: 1225726 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.0254. Min Act: -0.0000

Data Index: 586628 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.1526. Min Act: -0.0000

Data Index: 744554 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.1176. Min Act: -0.0000

Data Index: 980212 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.0350. Min Act: -0.0000

Data Index: 677915 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.9929. Min Act: -0.0000

Data Index: 948335 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.0674. Min Act: -0.0000

Data Index: 1071442 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.0114. Min Act: -0.0000

Data Index: 77070 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.9693. Min Act: 0.0000

Data Index: 1097921 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.0066. Min Act: -0.0000

Data Index: 220724 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.9666. Min Act: -0.0000

Data Index: 493186 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.9280. Min Act: -0.0000

Data Index: 637859 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.8829. Min Act: -0.0000

Data Index: 616163 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.9083. Min Act: -0.0000

Data Index: 555751 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1106428 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.9265. Min Act: -0.0000

Data Index: 859299 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.8745. Min Act: -0.0000

Data Index: 1204225 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.8981. Min Act: -0.0000

Data Index: 157020 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.8989. Min Act: -0.0000

Data Index: 515734 (C4 (Web Text))

Max Activating Token Index: 497