Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 105 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.2572. Min Range: -5.2572

Max Act: 5.2572. Min Act: -0.0000

Data Index: 1540259 (Python Code)

Max Activating Token Index: 242

Text #1

Max Range: 5.2572. Min Range: -5.2572

Max Act: 3.3505. Min Act: -0.0000

Data Index: 1632397 (Python Code)

Max Activating Token Index: 519

Text #2

Max Range: 5.2572. Min Range: -5.2572

Max Act: 3.1510. Min Act: -0.0000

Data Index: 1631985 (Python Code)

Max Activating Token Index: 384

Text #3

Max Range: 5.2572. Min Range: -5.2572

Max Act: 3.2986. Min Act: -0.0000

Data Index: 532288 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 5.2572. Min Range: -5.2572

Max Act: 3.1090. Min Act: -0.0000

Data Index: 1654154 (Python Code)

Max Activating Token Index: 259

Text #5

Max Range: 5.2572. Min Range: -5.2572

Max Act: 3.0000. Min Act: -0.0000

Data Index: 96719 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 5.2572. Min Range: -5.2572

Max Act: 2.9794. Min Act: -0.0000

Data Index: 1385437 (Python Code)

Max Activating Token Index: 80

Text #7

Max Range: 5.2572. Min Range: -5.2572

Max Act: 2.9699. Min Act: -0.0000

Data Index: 1541169 (Python Code)

Max Activating Token Index: 213

Text #8

Max Range: 5.2572. Min Range: -5.2572

Max Act: 2.9025. Min Act: -0.0000

Data Index: 1436125 (Python Code)

Max Activating Token Index: 65

Text #9

Max Range: 5.2572. Min Range: -5.2572

Max Act: 2.7357. Min Act: 0.0000

Data Index: 1093646 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 5.2572. Min Range: -5.2572

Max Act: 2.8840. Min Act: -0.0000

Data Index: 1647935 (Python Code)

Max Activating Token Index: 899

Text #11

Max Range: 5.2572. Min Range: -5.2572

Max Act: 2.6735. Min Act: -0.0000

Data Index: 1396454 (Python Code)

Max Activating Token Index: 713

Text #12

Max Range: 5.2572. Min Range: -5.2572

Max Act: 2.8010. Min Act: -0.0000

Data Index: 1582991 (Python Code)

Max Activating Token Index: 609

Text #13

Max Range: 5.2572. Min Range: -5.2572

Max Act: 2.7777. Min Act: -0.0000

Data Index: 1539952 (Python Code)

Max Activating Token Index: 352

Text #14

Max Range: 5.2572. Min Range: -5.2572

Max Act: 2.7735. Min Act: -0.0000

Data Index: 1492319 (Python Code)

Max Activating Token Index: 778

Text #15

Max Range: 5.2572. Min Range: -5.2572

Max Act: 2.6362. Min Act: -0.0000

Data Index: 1561266 (Python Code)

Max Activating Token Index: 948

Text #16

Max Range: 5.2572. Min Range: -5.2572

Max Act: 2.6329. Min Act: -0.0000

Data Index: 1587711 (Python Code)

Max Activating Token Index: 766

Text #17

Max Range: 5.2572. Min Range: -5.2572

Max Act: 2.8888. Min Act: -0.0000

Data Index: 1332651 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 5.2572. Min Range: -5.2572

Max Act: 2.5779. Min Act: -0.0000

Data Index: 952799 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 5.2572. Min Range: -5.2572

Max Act: 2.7088. Min Act: -0.0000

Data Index: 1512148 (Python Code)

Max Activating Token Index: 714