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

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

Neuron 1788 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0687. Min Range: -3.0687

Max Act: 3.0687. Min Act: -0.0000

Data Index: 931491 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.8383. Min Act: -0.0000

Data Index: 134634 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.7253. Min Act: -0.0000

Data Index: 513051 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.4950. Min Act: -0.0000

Data Index: 891004 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.2893. Min Act: -0.0000

Data Index: 112576 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.2717. Min Act: -0.0000

Data Index: 980476 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.2597. Min Act: -0.0000

Data Index: 1038958 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.2472. Min Act: -0.0000

Data Index: 182388 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.0799. Min Act: -0.0000

Data Index: 361799 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.1866. Min Act: -0.0000

Data Index: 561809 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.1111. Min Act: -0.0000

Data Index: 739686 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.1155. Min Act: -0.0000

Data Index: 1259219 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.1036. Min Act: -0.0000

Data Index: 20047 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.0807. Min Act: -0.0000

Data Index: 509120 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.0469. Min Act: -0.0000

Data Index: 1048270 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.0511. Min Act: -0.0000

Data Index: 192397 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.0397. Min Act: -0.0000

Data Index: 1354379 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.1210. Min Act: -0.0000

Data Index: 101866 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 3.0687. Min Range: -3.0687

Max Act: 2.0033. Min Act: -0.0000

Data Index: 178877 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 3.0687. Min Range: -3.0687

Max Act: 1.9930. Min Act: -0.0000

Data Index: 1274162 (C4 (Web Text))

Max Activating Token Index: 160