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

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

Neuron 1427 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.9234. Min Act: -0.0000

Data Index: 1524692 (Python Code)

Max Activating Token Index: 697

Text #1

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.4699. Min Act: -0.0000

Data Index: 1365187 (Python Code)

Max Activating Token Index: 631

Text #2

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.4906. Min Act: -0.0001

Data Index: 1366734 (Python Code)

Max Activating Token Index: 367

Text #3

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.4572. Min Act: -0.0000

Data Index: 598602 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.4713. Min Act: -0.0000

Data Index: 1632873 (Python Code)

Max Activating Token Index: 620

Text #5

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.4073. Min Act: -0.0000

Data Index: 1597541 (Python Code)

Max Activating Token Index: 413

Text #6

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.3897. Min Act: -0.0001

Data Index: 1523712 (Python Code)

Max Activating Token Index: 524

Text #7

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.2919. Min Act: -0.0000

Data Index: 1409673 (Python Code)

Max Activating Token Index: 807

Text #8

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.2291. Min Act: -0.0000

Data Index: 1375923 (Python Code)

Max Activating Token Index: 395

Text #9

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.3040. Min Act: -0.0000

Data Index: 1557628 (Python Code)

Max Activating Token Index: 217

Text #10

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.2502. Min Act: -0.0001

Data Index: 1462342 (Python Code)

Max Activating Token Index: 99

Text #11

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.1689. Min Act: -0.0000

Data Index: 1459927 (Python Code)

Max Activating Token Index: 128

Text #12

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.2029. Min Act: -0.0001

Data Index: 172925 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.1852. Min Act: -0.0001

Data Index: 1475153 (Python Code)

Max Activating Token Index: 261

Text #14

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.2188. Min Act: -0.0001

Data Index: 1421849 (Python Code)

Max Activating Token Index: 51

Text #15

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.2002. Min Act: -0.0001

Data Index: 1490321 (Python Code)

Max Activating Token Index: 432

Text #16

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.1719. Min Act: -0.0000

Data Index: 1530082 (Python Code)

Max Activating Token Index: 101

Text #17

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.1681. Min Act: -0.0001

Data Index: 1528052 (Python Code)

Max Activating Token Index: 656

Text #18

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.2145. Min Act: -0.0000

Data Index: 622748 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 1.9234. Min Range: -1.9234

Max Act: 1.1207. Min Act: -0.0000

Data Index: 1435552 (Python Code)

Max Activating Token Index: 670