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

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

Neuron 4035 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0395. Min Range: -1.0395

Max Act: 1.0395. Min Act: -0.0002

Data Index: 1583649 (Python Code)

Max Activating Token Index: 436

Text #1

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.7328. Min Act: -0.0002

Data Index: 1529112 (Python Code)

Max Activating Token Index: 405

Text #2

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.8402. Min Act: -0.0002

Data Index: 1606347 (Python Code)

Max Activating Token Index: 804

Text #3

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.7437. Min Act: -0.0002

Data Index: 1459639 (Python Code)

Max Activating Token Index: 304

Text #4

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.7895. Min Act: -0.0002

Data Index: 1543025 (Python Code)

Max Activating Token Index: 329

Text #5

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.7240. Min Act: -0.0002

Data Index: 1428049 (Python Code)

Max Activating Token Index: 627

Text #6

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.6864. Min Act: -0.0002

Data Index: 1588197 (Python Code)

Max Activating Token Index: 707

Text #7

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.6670. Min Act: -0.0002

Data Index: 1424223 (Python Code)

Max Activating Token Index: 932

Text #8

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.6782. Min Act: -0.0002

Data Index: 1590834 (Python Code)

Max Activating Token Index: 404

Text #9

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.6532. Min Act: -0.0002

Data Index: 1524361 (Python Code)

Max Activating Token Index: 743

Text #10

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.7172. Min Act: -0.0002

Data Index: 1563689 (Python Code)

Max Activating Token Index: 954

Text #11

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.6516. Min Act: -0.0002

Data Index: 1645706 (Python Code)

Max Activating Token Index: 971

Text #12

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.6422. Min Act: -0.0002

Data Index: 1480856 (Python Code)

Max Activating Token Index: 268

Text #13

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.6578. Min Act: -0.0002

Data Index: 1569100 (Python Code)

Max Activating Token Index: 399

Text #14

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.6757. Min Act: -0.0002

Data Index: 1476819 (Python Code)

Max Activating Token Index: 509

Text #15

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.6693. Min Act: -0.0002

Data Index: 1605505 (Python Code)

Max Activating Token Index: 614

Text #16

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.7262. Min Act: -0.0002

Data Index: 1366967 (Python Code)

Max Activating Token Index: 902

Text #17

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.6387. Min Act: -0.0002

Data Index: 1558625 (Python Code)

Max Activating Token Index: 493

Text #18

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.6156. Min Act: -0.0002

Data Index: 1576404 (Python Code)

Max Activating Token Index: 744

Text #19

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.7253. Min Act: -0.0002

Data Index: 1566815 (Python Code)

Max Activating Token Index: 841