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

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

Neuron 3417 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0526. Min Range: -4.0526

Max Act: 4.0526. Min Act: -0.0000

Data Index: 473355 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.8564. Min Act: -0.0000

Data Index: 1212091 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.7387. Min Act: -0.0001

Data Index: 44970 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.3362. Min Act: -0.0000

Data Index: 1041592 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.1606. Min Act: -0.0001

Data Index: 886408 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.1460. Min Act: -0.0001

Data Index: 910123 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.1668. Min Act: -0.0001

Data Index: 837454 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 4.0526. Min Range: -4.0526

Max Act: 2.9796. Min Act: -0.0001

Data Index: 90735 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.0402. Min Act: -0.0001

Data Index: 1031748 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 4.0526. Min Range: -4.0526

Max Act: 2.8644. Min Act: -0.0001

Data Index: 13857 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 4.0526. Min Range: -4.0526

Max Act: 2.8707. Min Act: -0.0000

Data Index: 685588 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 4.0526. Min Range: -4.0526

Max Act: 2.9393. Min Act: -0.0000

Data Index: 609032 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.0255. Min Act: -0.0000

Data Index: 844140 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 4.0526. Min Range: -4.0526

Max Act: 2.8840. Min Act: -0.0001

Data Index: 29488 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 4.0526. Min Range: -4.0526

Max Act: 2.9820. Min Act: -0.0000

Data Index: 447782 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 4.0526. Min Range: -4.0526

Max Act: 2.6958. Min Act: -0.0000

Data Index: 829623 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 4.0526. Min Range: -4.0526

Max Act: 2.7799. Min Act: -0.0001

Data Index: 600341 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 4.0526. Min Range: -4.0526

Max Act: 2.7796. Min Act: -0.0000

Data Index: 1133462 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 4.0526. Min Range: -4.0526

Max Act: 2.7568. Min Act: -0.0000

Data Index: 314933 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 4.0526. Min Range: -4.0526

Max Act: 2.7208. Min Act: -0.0001

Data Index: 1306254 (C4 (Web Text))

Max Activating Token Index: 573