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

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

Neuron 6109 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1403. Min Range: -2.1403

Max Act: 2.1403. Min Act: -0.0000

Data Index: 102027 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 2.1403. Min Range: -2.1403

Max Act: 1.1266. Min Act: -0.0000

Data Index: 1241442 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 2.1403. Min Range: -2.1403

Max Act: 1.0563. Min Act: -0.0000

Data Index: 336000 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 2.1403. Min Range: -2.1403

Max Act: 1.0848. Min Act: -0.0000

Data Index: 787887 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 2.1403. Min Range: -2.1403

Max Act: 1.0433. Min Act: -0.0000

Data Index: 838079 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 2.1403. Min Range: -2.1403

Max Act: 1.0917. Min Act: -0.0000

Data Index: 298381 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 2.1403. Min Range: -2.1403

Max Act: 1.0802. Min Act: -0.0000

Data Index: 915645 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 2.1403. Min Range: -2.1403

Max Act: 1.0661. Min Act: -0.0000

Data Index: 187459 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 2.1403. Min Range: -2.1403

Max Act: 1.0530. Min Act: -0.0000

Data Index: 867873 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 2.1403. Min Range: -2.1403

Max Act: 1.1163. Min Act: -0.0000

Data Index: 760893 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 2.1403. Min Range: -2.1403

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1015997 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 2.1403. Min Range: -2.1403

Max Act: 1.1014. Min Act: -0.0000

Data Index: 834261 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 2.1403. Min Range: -2.1403

Max Act: 1.0146. Min Act: -0.0000

Data Index: 374657 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 2.1403. Min Range: -2.1403

Max Act: 1.0133. Min Act: -0.0000

Data Index: 587487 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 2.1403. Min Range: -2.1403

Max Act: 0.9469. Min Act: -0.0000

Data Index: 1088759 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 2.1403. Min Range: -2.1403

Max Act: 1.0057. Min Act: -0.0000

Data Index: 1201014 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 2.1403. Min Range: -2.1403

Max Act: 1.0567. Min Act: -0.0000

Data Index: 822366 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 2.1403. Min Range: -2.1403

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1074033 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 2.1403. Min Range: -2.1403

Max Act: 0.9499. Min Act: -0.0000

Data Index: 752569 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 2.1403. Min Range: -2.1403

Max Act: 0.9505. Min Act: -0.0000

Data Index: 1137942 (C4 (Web Text))

Max Activating Token Index: 274