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

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

Neuron 4586 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.7643. Min Act: -0.0000

Data Index: 419392 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.5619. Min Act: -0.0000

Data Index: 737133 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.5470. Min Act: -0.0000

Data Index: 641054 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.6673. Min Act: -0.0000

Data Index: 552706 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.9845. Min Act: -0.0000

Data Index: 671486 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.3056. Min Act: -0.0000

Data Index: 475139 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.3436. Min Act: -0.0000

Data Index: 1093722 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.6449. Min Act: -0.0000

Data Index: 662271 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.4282. Min Act: -0.0000

Data Index: 679993 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.3281. Min Act: -0.0000

Data Index: 301247 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.3168. Min Act: -0.0000

Data Index: 944496 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.1493. Min Act: -0.0000

Data Index: 783639 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.1050. Min Act: -0.0000

Data Index: 763623 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.1938. Min Act: -0.0000

Data Index: 597894 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.0856. Min Act: -0.0000

Data Index: 518423 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.3284. Min Act: -0.0000

Data Index: 867439 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.0529. Min Act: -0.0000

Data Index: 908530 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.3398. Min Act: -0.0000

Data Index: 1137103 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.1517. Min Act: -0.0000

Data Index: 1147347 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.1676. Min Act: -0.0000

Data Index: 124622 (C4 (Web Text))

Max Activating Token Index: 585