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

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

Neuron 4890 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.6737. Min Act: -0.0000

Data Index: 1385069 (Python Code)

Max Activating Token Index: 149

Text #1

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.6170. Min Act: -0.0000

Data Index: 1391485 (Python Code)

Max Activating Token Index: 577

Text #2

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.5461. Min Act: -0.0000

Data Index: 1479772 (Python Code)

Max Activating Token Index: 975

Text #3

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.3809. Min Act: -0.0000

Data Index: 1486194 (Python Code)

Max Activating Token Index: 783

Text #4

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.4178. Min Act: -0.0000

Data Index: 1381284 (Python Code)

Max Activating Token Index: 258

Text #5

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.3155. Min Act: -0.0000

Data Index: 1338944 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.2436. Min Act: -0.0000

Data Index: 1374472 (Python Code)

Max Activating Token Index: 230

Text #7

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.4544. Min Act: -0.0000

Data Index: 1439684 (Python Code)

Max Activating Token Index: 305

Text #8

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.2481. Min Act: -0.0000

Data Index: 326608 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.3449. Min Act: -0.0000

Data Index: 739921 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.1917. Min Act: -0.0000

Data Index: 984996 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.2139. Min Act: -0.0000

Data Index: 1641644 (Python Code)

Max Activating Token Index: 396

Text #12

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.3610. Min Act: -0.0000

Data Index: 1537168 (Python Code)

Max Activating Token Index: 1022

Text #13

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1407054 (Python Code)

Max Activating Token Index: 102

Text #14

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.1706. Min Act: -0.0000

Data Index: 1580770 (Python Code)

Max Activating Token Index: 602

Text #15

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1620858 (Python Code)

Max Activating Token Index: 389

Text #16

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.2031. Min Act: -0.0000

Data Index: 1446236 (Python Code)

Max Activating Token Index: 963

Text #17

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.1608. Min Act: -0.0000

Data Index: 1612661 (Python Code)

Max Activating Token Index: 108

Text #18

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.1406. Min Act: -0.0000

Data Index: 1609476 (Python Code)

Max Activating Token Index: 535

Text #19

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.1918. Min Act: -0.0000

Data Index: 1465629 (Python Code)

Max Activating Token Index: 442