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

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

Neuron 1783 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: 1.4522. Min Range: -1.4522

Max Act: 1.4522. Min Act: -0.0000

Data Index: 1496569 (Python Code)

Max Activating Token Index: 1009

Text #1

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2777. Min Act: -0.0000

Data Index: 529218 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.3333. Min Act: -0.0000

Data Index: 1523729 (Python Code)

Max Activating Token Index: 1018

Text #3

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.3025. Min Act: -0.0000

Data Index: 14324 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2974. Min Act: -0.0000

Data Index: 1388664 (Python Code)

Max Activating Token Index: 870

Text #5

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2839. Min Act: -0.0000

Data Index: 1361460 (Python Code)

Max Activating Token Index: 197

Text #6

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2472. Min Act: -0.0000

Data Index: 1417360 (Python Code)

Max Activating Token Index: 398

Text #7

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2401. Min Act: -0.0000

Data Index: 138978 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2630. Min Act: -0.0000

Data Index: 1581593 (Python Code)

Max Activating Token Index: 399

Text #9

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.1478. Min Act: -0.0000

Data Index: 730893 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2782. Min Act: -0.0000

Data Index: 1609788 (Python Code)

Max Activating Token Index: 636

Text #11

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2419. Min Act: -0.0000

Data Index: 1624835 (Python Code)

Max Activating Token Index: 511

Text #12

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.1532. Min Act: -0.0000

Data Index: 899748 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.1717. Min Act: -0.0000

Data Index: 428634 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.1670. Min Act: -0.0000

Data Index: 1571025 (Python Code)

Max Activating Token Index: 963

Text #15

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.1523. Min Act: -0.0000

Data Index: 1637571 (Python Code)

Max Activating Token Index: 711

Text #16

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.1402. Min Act: -0.0000

Data Index: 1181546 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.1957. Min Act: -0.0000

Data Index: 1550043 (Python Code)

Max Activating Token Index: 176

Text #18

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.0871. Min Act: -0.0000

Data Index: 1645197 (Python Code)

Max Activating Token Index: 516

Text #19

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.0620. Min Act: -0.0000

Data Index: 325900 (C4 (Web Text))

Max Activating Token Index: 874