Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 900 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1225. Min Act: -0.0001

Data Index: 863766 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0918. Min Act: -0.0001

Data Index: 85228 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0890. Min Act: -0.0001

Data Index: 408566 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0858. Min Act: -0.0001

Data Index: 1250136 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0831. Min Act: -0.0001

Data Index: 656066 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0762. Min Act: -0.0001

Data Index: 292489 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0792. Min Act: -0.0001

Data Index: 1078089 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0820. Min Act: -0.0001

Data Index: 119231 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1182723 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0811. Min Act: -0.0001

Data Index: 645446 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0792. Min Act: -0.0001

Data Index: 1335131 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0789. Min Act: -0.0001

Data Index: 154954 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1301650 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0746. Min Act: -0.0001

Data Index: 467645 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0742. Min Act: -0.0001

Data Index: 290082 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1079124 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1349129 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0731. Min Act: -0.0001

Data Index: 542188 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0753. Min Act: -0.0001

Data Index: 548240 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0734. Min Act: -0.0001

Data Index: 1141129 (C4 (Web Text))

Max Activating Token Index: 473