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

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

Neuron 821 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1403. Min Range: -5.1403

Max Act: 5.1403. Min Act: -0.0000

Data Index: 1311088 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 5.1403. Min Range: -5.1403

Max Act: 4.9521. Min Act: -0.0000

Data Index: 1183601 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 5.1403. Min Range: -5.1403

Max Act: 5.0862. Min Act: -0.0000

Data Index: 287807 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 5.1403. Min Range: -5.1403

Max Act: 4.8124. Min Act: -0.0000

Data Index: 953090 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 5.1403. Min Range: -5.1403

Max Act: 4.9713. Min Act: -0.0000

Data Index: 962043 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 5.1403. Min Range: -5.1403

Max Act: 4.7286. Min Act: -0.0000

Data Index: 1359385 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 5.1403. Min Range: -5.1403

Max Act: 4.5285. Min Act: -0.0000

Data Index: 636546 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 5.1403. Min Range: -5.1403

Max Act: 4.6657. Min Act: -0.0000

Data Index: 303379 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 5.1403. Min Range: -5.1403

Max Act: 4.5511. Min Act: -0.0000

Data Index: 950267 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 5.1403. Min Range: -5.1403

Max Act: 4.6933. Min Act: -0.0000

Data Index: 1209136 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 5.1403. Min Range: -5.1403

Max Act: 4.6219. Min Act: -0.0000

Data Index: 217716 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 5.1403. Min Range: -5.1403

Max Act: 4.5377. Min Act: -0.0000

Data Index: 97340 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 5.1403. Min Range: -5.1403

Max Act: 4.5244. Min Act: -0.0000

Data Index: 503161 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 5.1403. Min Range: -5.1403

Max Act: 4.2754. Min Act: -0.0000

Data Index: 814244 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 5.1403. Min Range: -5.1403

Max Act: 4.2646. Min Act: -0.0000

Data Index: 1166989 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 5.1403. Min Range: -5.1403

Max Act: 4.2369. Min Act: -0.0000

Data Index: 65871 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 5.1403. Min Range: -5.1403

Max Act: 4.1809. Min Act: -0.0000

Data Index: 1283699 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 5.1403. Min Range: -5.1403

Max Act: 3.5103. Min Act: -0.0000

Data Index: 720640 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 5.1403. Min Range: -5.1403

Max Act: 3.6454. Min Act: -0.0000

Data Index: 774438 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 5.1403. Min Range: -5.1403

Max Act: 3.9233. Min Act: -0.0000

Data Index: 1027872 (C4 (Web Text))

Max Activating Token Index: 499