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

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

Neuron 2468 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1803. Min Act: -0.0003

Data Index: 550394 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1796. Min Act: -0.0003

Data Index: 1047498 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1830. Min Act: -0.0003

Data Index: 204584 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.2066. Min Act: -0.0003

Data Index: 876620 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1668. Min Act: -0.0003

Data Index: 740093 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1730. Min Act: -0.0003

Data Index: 956727 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1825. Min Act: -0.0003

Data Index: 784059 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1611. Min Act: -0.0003

Data Index: 73058 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1613. Min Act: -0.0003

Data Index: 1306703 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1672. Min Act: -0.0003

Data Index: 1059971 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1506. Min Act: -0.0003

Data Index: 1238772 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1500. Min Act: -0.0003

Data Index: 982 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1735. Min Act: -0.0003

Data Index: 832447 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1561. Min Act: -0.0003

Data Index: 393155 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1512. Min Act: -0.0003

Data Index: 747840 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1464. Min Act: -0.0003

Data Index: 1167404 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1455. Min Act: -0.0003

Data Index: 563333 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1667. Min Act: -0.0003

Data Index: 892137 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1516. Min Act: -0.0003

Data Index: 1148127 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1504. Min Act: -0.0003

Data Index: 147487 (C4 (Web Text))

Max Activating Token Index: 498