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

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

Neuron 1474 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1480934 (Python Code)

Max Activating Token Index: 329

Text #1

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1576832 (Python Code)

Max Activating Token Index: 600

Text #2

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3485. Min Act: -0.0000

Data Index: 1375760 (Python Code)

Max Activating Token Index: 405

Text #3

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1592284 (Python Code)

Max Activating Token Index: 642

Text #4

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1335577 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2969. Min Act: -0.0000

Data Index: 867715 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2873. Min Act: -0.0000

Data Index: 1639177 (Python Code)

Max Activating Token Index: 97

Text #7

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2933. Min Act: -0.0000

Data Index: 630486 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1037572 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3075. Min Act: -0.0001

Data Index: 1408964 (Python Code)

Max Activating Token Index: 679

Text #10

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2822. Min Act: -0.0000

Data Index: 1173278 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2960. Min Act: -0.0000

Data Index: 896716 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2874. Min Act: -0.0000

Data Index: 97689 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2789. Min Act: -0.0000

Data Index: 133914 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2759. Min Act: -0.0000

Data Index: 1590360 (Python Code)

Max Activating Token Index: 225

Text #15

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1387534 (Python Code)

Max Activating Token Index: 916

Text #16

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1313149 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1466556 (Python Code)

Max Activating Token Index: 637

Text #18

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2761. Min Act: -0.0000

Data Index: 1503642 (Python Code)

Max Activating Token Index: 981

Text #19

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2677. Min Act: -0.0000

Data Index: 1565438 (Python Code)

Max Activating Token Index: 751