Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2076 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.5905. Min Act: -0.0003

Data Index: 1525117 (Python Code)

Max Activating Token Index: 635

Text #1

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.5700. Min Act: -0.0002

Data Index: 1503757 (Python Code)

Max Activating Token Index: 660

Text #2

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.5621. Min Act: -0.0003

Data Index: 1497261 (Python Code)

Max Activating Token Index: 829

Text #3

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.5525. Min Act: -0.0002

Data Index: 1548031 (Python Code)

Max Activating Token Index: 558

Text #4

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.5327. Min Act: -0.0002

Data Index: 1496129 (Python Code)

Max Activating Token Index: 150

Text #5

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.5546. Min Act: -0.0002

Data Index: 1631700 (Python Code)

Max Activating Token Index: 835

Text #6

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.5351. Min Act: -0.0002

Data Index: 1414981 (Python Code)

Max Activating Token Index: 390

Text #7

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.5282. Min Act: -0.0003

Data Index: 1369658 (Python Code)

Max Activating Token Index: 563

Text #8

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.5033. Min Act: -0.0003

Data Index: 452838 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4982. Min Act: -0.0003

Data Index: 705749 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.5028. Min Act: -0.0002

Data Index: 1656486 (Python Code)

Max Activating Token Index: 794

Text #11

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4845. Min Act: -0.0002

Data Index: 1482632 (Python Code)

Max Activating Token Index: 716

Text #12

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4887. Min Act: -0.0002

Data Index: 1574132 (Python Code)

Max Activating Token Index: 326

Text #13

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4696. Min Act: -0.0003

Data Index: 1271522 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4751. Min Act: -0.0002

Data Index: 1530662 (Python Code)

Max Activating Token Index: 396

Text #15

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4680. Min Act: -0.0002

Data Index: 1529418 (Python Code)

Max Activating Token Index: 327

Text #16

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4669. Min Act: -0.0002

Data Index: 717376 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4646. Min Act: -0.0002

Data Index: 1568893 (Python Code)

Max Activating Token Index: 315

Text #18

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4747. Min Act: -0.0002

Data Index: 1525563 (Python Code)

Max Activating Token Index: 920

Text #19

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4574. Min Act: -0.0002

Data Index: 882571 (C4 (Web Text))

Max Activating Token Index: 564