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

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

Neuron 2238 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1388935 (Python Code)

Max Activating Token Index: 443

Text #1

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1243181 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1407008 (Python Code)

Max Activating Token Index: 730

Text #3

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1547363 (Python Code)

Max Activating Token Index: 369

Text #4

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1516278 (Python Code)

Max Activating Token Index: 521

Text #5

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1363632 (Python Code)

Max Activating Token Index: 638

Text #6

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1584461 (Python Code)

Max Activating Token Index: 677

Text #7

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1614. Min Act: -0.0000

Data Index: 1444930 (Python Code)

Max Activating Token Index: 152

Text #8

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1553035 (Python Code)

Max Activating Token Index: 592

Text #9

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1567180 (Python Code)

Max Activating Token Index: 886

Text #10

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1557142 (Python Code)

Max Activating Token Index: 240

Text #11

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1511196 (Python Code)

Max Activating Token Index: 305

Text #12

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1363811 (Python Code)

Max Activating Token Index: 937

Text #13

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1587191 (Python Code)

Max Activating Token Index: 431

Text #14

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1563223 (Python Code)

Max Activating Token Index: 716

Text #15

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1506. Min Act: -0.0000

Data Index: 1490572 (Python Code)

Max Activating Token Index: 746

Text #16

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1493. Min Act: -0.0000

Data Index: 1397626 (Python Code)

Max Activating Token Index: 342

Text #17

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1420. Min Act: -0.0000

Data Index: 235943 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1516. Min Act: -0.0000

Data Index: 864136 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1507322 (Python Code)

Max Activating Token Index: 538