Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2835 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0959. Min Range: -1.0959

Max Act: 1.0959. Min Act: -0.0001

Data Index: 179524 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.8665. Min Act: -0.0001

Data Index: 1387818 (Python Code)

Max Activating Token Index: 94

Text #2

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.8104. Min Act: -0.0001

Data Index: 1492416 (Python Code)

Max Activating Token Index: 116

Text #3

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.7796. Min Act: -0.0001

Data Index: 1654611 (Python Code)

Max Activating Token Index: 28

Text #4

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.7705. Min Act: -0.0001

Data Index: 1500771 (Python Code)

Max Activating Token Index: 890

Text #5

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.7693. Min Act: -0.0001

Data Index: 1376821 (Python Code)

Max Activating Token Index: 697

Text #6

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.6782. Min Act: -0.0001

Data Index: 1655259 (Python Code)

Max Activating Token Index: 708

Text #7

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.6768. Min Act: -0.0001

Data Index: 1458530 (Python Code)

Max Activating Token Index: 315

Text #8

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.7391. Min Act: -0.0001

Data Index: 1378798 (Python Code)

Max Activating Token Index: 680

Text #9

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.7152. Min Act: -0.0001

Data Index: 693084 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.7047. Min Act: -0.0001

Data Index: 1559837 (Python Code)

Max Activating Token Index: 246

Text #11

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.7033. Min Act: -0.0001

Data Index: 1475673 (Python Code)

Max Activating Token Index: 239

Text #12

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.6990. Min Act: -0.0001

Data Index: 1375697 (Python Code)

Max Activating Token Index: 409

Text #13

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.6460. Min Act: -0.0001

Data Index: 1383478 (Python Code)

Max Activating Token Index: 454

Text #14

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.6822. Min Act: -0.0001

Data Index: 1444564 (Python Code)

Max Activating Token Index: 93

Text #15

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.6525. Min Act: -0.0001

Data Index: 1411551 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.6743. Min Act: -0.0001

Data Index: 1516412 (Python Code)

Max Activating Token Index: 396

Text #17

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.6043. Min Act: -0.0001

Data Index: 1474587 (Python Code)

Max Activating Token Index: 650

Text #18

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.6924. Min Act: -0.0001

Data Index: 1575970 (Python Code)

Max Activating Token Index: 469

Text #19

Max Range: 1.0959. Min Range: -1.0959

Max Act: 0.6438. Min Act: -0.0001

Data Index: 1584107 (Python Code)

Max Activating Token Index: 656