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

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

Neuron 2409 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: 2.3501. Min Range: -2.3501

Max Act: 2.1944. Min Act: -0.0000

Data Index: 894929 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 2.3501. Min Range: -2.3501

Max Act: 2.3501. Min Act: -0.0000

Data Index: 158260 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 2.3501. Min Range: -2.3501

Max Act: 2.0584. Min Act: -0.0000

Data Index: 617337 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 2.3501. Min Range: -2.3501

Max Act: 2.1483. Min Act: -0.0000

Data Index: 1098750 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 2.3501. Min Range: -2.3501

Max Act: 2.0454. Min Act: 0.0000

Data Index: 873547 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 2.3501. Min Range: -2.3501

Max Act: 1.7425. Min Act: -0.0000

Data Index: 410507 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 2.3501. Min Range: -2.3501

Max Act: 1.9014. Min Act: -0.0000

Data Index: 108490 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 2.3501. Min Range: -2.3501

Max Act: 1.8780. Min Act: -0.0000

Data Index: 852309 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 2.3501. Min Range: -2.3501

Max Act: 1.8133. Min Act: -0.0000

Data Index: 508837 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 2.3501. Min Range: -2.3501

Max Act: 1.7069. Min Act: -0.0000

Data Index: 893803 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 2.3501. Min Range: -2.3501

Max Act: 1.6640. Min Act: 0.0000

Data Index: 822189 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 2.3501. Min Range: -2.3501

Max Act: 1.6525. Min Act: -0.0000

Data Index: 1110109 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 2.3501. Min Range: -2.3501

Max Act: 1.7233. Min Act: -0.0000

Data Index: 1295352 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 2.3501. Min Range: -2.3501

Max Act: 1.5743. Min Act: -0.0000

Data Index: 1301429 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 2.3501. Min Range: -2.3501

Max Act: 1.5830. Min Act: -0.0000

Data Index: 1297817 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 2.3501. Min Range: -2.3501

Max Act: 1.5402. Min Act: -0.0000

Data Index: 721761 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 2.3501. Min Range: -2.3501

Max Act: 1.6276. Min Act: 0.0000

Data Index: 710197 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 2.3501. Min Range: -2.3501

Max Act: 1.5381. Min Act: -0.0000

Data Index: 1352611 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 2.3501. Min Range: -2.3501

Max Act: 1.4446. Min Act: -0.0000

Data Index: 794095 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 2.3501. Min Range: -2.3501

Max Act: 1.4136. Min Act: -0.0000

Data Index: 384052 (C4 (Web Text))

Max Activating Token Index: 432