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

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

Neuron 2478 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1572076 (Python Code)

Max Activating Token Index: 949

Text #1

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1416187 (Python Code)

Max Activating Token Index: 516

Text #2

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1061025 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1532199 (Python Code)

Max Activating Token Index: 631

Text #4

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1619145 (Python Code)

Max Activating Token Index: 742

Text #5

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1451785 (Python Code)

Max Activating Token Index: 831

Text #6

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1616290 (Python Code)

Max Activating Token Index: 904

Text #7

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1483357 (Python Code)

Max Activating Token Index: 230

Text #8

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1605240 (Python Code)

Max Activating Token Index: 944

Text #9

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1474417 (Python Code)

Max Activating Token Index: 384

Text #10

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1516085 (Python Code)

Max Activating Token Index: 626

Text #11

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1211954 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.2142. Min Act: -0.0000

Data Index: 1445312 (Python Code)

Max Activating Token Index: 371

Text #13

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.1672. Min Act: -0.0000

Data Index: 1445867 (Python Code)

Max Activating Token Index: 496

Text #14

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.1813. Min Act: -0.0000

Data Index: 322304 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.1760. Min Act: -0.0000

Data Index: 89214 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1414975 (Python Code)

Max Activating Token Index: 711

Text #17

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.1792. Min Act: -0.0000

Data Index: 253510 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.1808. Min Act: -0.0000

Data Index: 200162 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.2376. Min Range: -0.2376

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1481453 (Python Code)

Max Activating Token Index: 615