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

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

Neuron 542 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1915. Min Range: -2.1915

Max Act: 2.1361. Min Act: -0.0000

Data Index: 1410938 (Python Code)

Max Activating Token Index: 664

Text #1

Max Range: 2.1915. Min Range: -2.1915

Max Act: 2.1915. Min Act: -0.0000

Data Index: 1611429 (Python Code)

Max Activating Token Index: 669

Text #2

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.9084. Min Act: -0.0000

Data Index: 1379229 (Python Code)

Max Activating Token Index: 143

Text #3

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.9882. Min Act: -0.0000

Data Index: 1369951 (Python Code)

Max Activating Token Index: 691

Text #4

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.9812. Min Act: -0.0000

Data Index: 1423099 (Python Code)

Max Activating Token Index: 497

Text #5

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.9203. Min Act: -0.0000

Data Index: 1512105 (Python Code)

Max Activating Token Index: 517

Text #6

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.8044. Min Act: -0.0000

Data Index: 1535258 (Python Code)

Max Activating Token Index: 68

Text #7

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.8882. Min Act: -0.0000

Data Index: 1453173 (Python Code)

Max Activating Token Index: 967

Text #8

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.8875. Min Act: -0.0000

Data Index: 1529077 (Python Code)

Max Activating Token Index: 341

Text #9

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.8624. Min Act: -0.0000

Data Index: 1620781 (Python Code)

Max Activating Token Index: 299

Text #10

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.8430. Min Act: -0.0000

Data Index: 1531561 (Python Code)

Max Activating Token Index: 647

Text #11

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.8410. Min Act: -0.0000

Data Index: 1463777 (Python Code)

Max Activating Token Index: 353

Text #12

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.8264. Min Act: -0.0000

Data Index: 1561772 (Python Code)

Max Activating Token Index: 566

Text #13

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.8233. Min Act: -0.0000

Data Index: 1445822 (Python Code)

Max Activating Token Index: 267

Text #14

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.7802. Min Act: -0.0000

Data Index: 1468755 (Python Code)

Max Activating Token Index: 883

Text #15

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.7723. Min Act: -0.0000

Data Index: 1597730 (Python Code)

Max Activating Token Index: 601

Text #16

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.6791. Min Act: -0.0000

Data Index: 1557311 (Python Code)

Max Activating Token Index: 274

Text #17

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.7614. Min Act: -0.0000

Data Index: 1527767 (Python Code)

Max Activating Token Index: 416

Text #18

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.7744. Min Act: -0.0000

Data Index: 1517316 (Python Code)

Max Activating Token Index: 231

Text #19

Max Range: 2.1915. Min Range: -2.1915

Max Act: 1.6617. Min Act: -0.0000

Data Index: 1487004 (Python Code)

Max Activating Token Index: 778