Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1706 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1944. Min Act: -0.0001

Data Index: 1239834 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1814. Min Act: -0.0000

Data Index: 409854 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1732. Min Act: -0.0001

Data Index: 784760 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1752. Min Act: -0.0001

Data Index: 10644 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1686. Min Act: -0.0001

Data Index: 1085597 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1612. Min Act: -0.0001

Data Index: 247234 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1609. Min Act: -0.0001

Data Index: 358908 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1455. Min Act: -0.0001

Data Index: 702890 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1477. Min Act: -0.0000

Data Index: 968633 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1540. Min Act: -0.0001

Data Index: 72909 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1525. Min Act: -0.0001

Data Index: 649612 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1479. Min Act: -0.0001

Data Index: 341373 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1521. Min Act: -0.0001

Data Index: 351469 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1522. Min Act: -0.0001

Data Index: 1237084 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1499. Min Act: -0.0000

Data Index: 813079 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1445. Min Act: -0.0001

Data Index: 495820 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1341801 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1478. Min Act: -0.0000

Data Index: 265733 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1488. Min Act: -0.0001

Data Index: 115582 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1550. Min Act: -0.0001

Data Index: 92656 (C4 (Web Text))

Max Activating Token Index: 205